Koskamo

SanYu Research Engine MCP

An MCP server providing 106 deterministic medical research engines for statistics, survival analysis, bioinformatics, and primer design. It uses real algorithms with engine_status verification to prevent LLM hallucination, supporting agents like Claude and Cursor via Streamable HTTP.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

SanYu Research Engine MCP logo, by kfx2026Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by kfx2026
MCP endpoint (Streamable HTTP)
https://sanyu.wentangkeji.com/api/mcp
Vendor documentation

What its tools do

106 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (106)

106 of 106 have a description · 106 of 106 declare behavior hints · 103 of 103 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Perform statistical analysis including ROC/AUC and survival analysis
  • Conduct bioinformatics tasks like GO/KEGG enrichment and PPI networks
  • Design primers and calculate Tm for molecular biology experiments
  • Retrieve literature via PubMed and internal full-text search

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.kfx2026/sanyu-research@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
sanyu-research 1.1.0
MCP protocol negotiated in check
2025-06-18
Tools
106 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

三域医研是**真算法**医学科研引擎，不是大模型套壳。每个工具背后是确定性实现（SciPy/statsmodels/自研 MCTS/DESeq2-like 负二项/生信算子），返回体强制带 engine_status（real / unavailable / error）与 data_source。引擎不可用时如实返回 unavailable 而**不会编造结果**——请如实转述这两个字段。 本服务器把 105 个动作作为独立工具暴露（名字即动作 id，如 act_roc / act_deg_analyze），参数 schema 见各工具 inputSchema。仅在不确定该用哪个动作时调用 sanyu_list_actions。 开放的只有**计算类**动作：不会写入任何项目或用户数据（传 project_id 会被忽略并在 warnings 说明）。 执行需要在 HTTP 头带 Authorization: Bearer sk-sanyu-xxx（在 https://sanyu.wentangkeji.com 的「API 密钥」页生成，注册送试用积分）。缺参数时返回 hint_fields，按它补齐重试即可（缺参不扣分）。

Tools

106 advertised

act_animal_arrive_check
Advertised by the server during the last successful anonymous check.
Advertised read-only

【ARRIVE 2.0 检查】 用户问动物实验符不符合 ARRIVE 2.0 返回：ARRIVE 条目核对 （真实算法引擎执行，非大模型生成）

act_animal_arrive_check input schema
{
  "type": "object",
  "required": [],
  "properties": {}
}
act_animal_arrive_check annotations
{
  "title": "ARRIVE 2.0 检查",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_animal_dosing
Advertised by the server during the last successful anonymous check.
Advertised read-only

【动物给药量计算】 用户要按体重算给药体积/剂量 返回：给药量与体积 （真实算法引擎执行，非大模型生成）

act_animal_dosing input schema
{
  "type": "object",
  "required": [
    "animal_weight_g",
    "dose_mg_per_kg"
  ],
  "properties": {
    "dose_mg_per_kg": {
      "type": "number",
      "description": "剂量(mg/kg)"
    },
    "animal_weight_g": {
      "type": "number",
      "description": "动物体重(g)"
    }
  }
}
act_animal_dosing annotations
{
  "title": "动物给药量计算",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_animal_organ_coef
Advertised by the server during the last successful anonymous check.
Advertised read-only

【脏器系数】 用户要算脏器系数（脏器重/体重） 返回：脏器系数 （真实算法引擎执行，非大模型生成）

act_animal_organ_coef input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "label": {
      "type": "string",
      "description": "脏器名"
    },
    "body_weights": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "体重"
    },
    "organ_weights": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "脏器重"
    }
  }
}
act_animal_organ_coef annotations
{
  "title": "脏器系数",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_animal_randomize
Advertised by the server during the last successful anonymous check.
Advertised read-only

【动物随机分组】 用户要把动物随机分组（ARRIVE 要求） 返回：分组表 （真实算法引擎执行，非大模型生成）

act_animal_randomize input schema
{
  "type": "object",
  "required": [
    "n_total"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "description": "种子"
    },
    "groups": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "分组名"
    },
    "method": {
      "type": "string",
      "description": "随机化方法"
    },
    "n_total": {
      "type": "integer",
      "description": "动物总数"
    }
  }
}
act_animal_randomize annotations
{
  "title": "动物随机分组",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_animal_sample_size
Advertised by the server during the last successful anonymous check.
Advertised read-only

【动物实验样本量】 用户问动物实验要多少只、ARRIVE 要求怎么写 返回：每组动物数 （真实算法引擎执行，非大模型生成）

act_animal_sample_size input schema
{
  "type": "object",
  "required": [
    "effect_size"
  ],
  "properties": {
    "alpha": {
      "type": "number",
      "description": "α"
    },
    "power": {
      "type": "number",
      "description": "把握度"
    },
    "groups": {
      "type": "integer",
      "description": "组数"
    },
    "effect_size": {
      "type": "number",
      "description": "效应量"
    }
  }
}
act_animal_sample_size annotations
{
  "title": "动物实验样本量",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_animal_survival
Advertised by the server during the last successful anonymous check.
Advertised read-only

【动物生存分析】 用户有动物死亡时间要做生存曲线 返回：KM 曲线与 log-rank （真实算法引擎执行，非大模型生成）

act_animal_survival input schema
{
  "type": "object",
  "required": [
    "ctrl_times",
    "ctrl_events",
    "treat_times",
    "treat_events"
  ],
  "properties": {
    "ctrl_times": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "对照组时间"
    },
    "ctrl_events": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "对照组事件"
    },
    "treat_times": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "给药组时间"
    },
    "treat_events": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "给药组事件"
    }
  }
}
act_animal_survival annotations
{
  "title": "动物生存分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_animal_tgi
Advertised by the server during the last successful anonymous check.
Advertised read-only

【抑瘤率 TGI】 用户要算抑瘤率 TGI 返回：TGI 与统计检验 （真实算法引擎执行，非大模型生成）

act_animal_tgi input schema
{
  "type": "object",
  "required": [
    "ctrl_volumes",
    "treat_volumes"
  ],
  "properties": {
    "ctrl_volumes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "对照组体积"
    },
    "treat_volumes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "给药组体积"
    }
  }
}
act_animal_tgi annotations
{
  "title": "抑瘤率 TGI",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_animal_tumor_volume
Advertised by the server during the last successful anonymous check.
Advertised read-only

【肿瘤体积计算】 用户有长宽数据要算肿瘤体积与生长曲线 返回：体积与生长曲线 （真实算法引擎执行，非大模型生成）

act_animal_tumor_volume input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "days": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "天数"
    },
    "widths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "短径"
    },
    "lengths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "长径"
    },
    "group_name": {
      "type": "string",
      "description": "组名"
    }
  }
}
act_animal_tumor_volume annotations
{
  "title": "肿瘤体积计算",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_atac_diff
Advertised by the server during the last successful anonymous check.
Advertised read-only

【ATAC 差异可及性】 用户有 ATAC-seq 要做差异开放区域 返回：差异 peak （真实算法引擎执行，非大模型生成）

act_atac_diff input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "data_json": {
      "type": "object",
      "description": "必填。数据对象（不是字符串）。矩阵形式：{\"matrix\": [[行1各列数值...], [行2...]], \"rows\": [\"基因/特征名\"], \"cols\": [\"样本名\"]}；组学结果另可带 {\"groups\": [\"组A\",\"组A\",\"组B\"...]}（与 cols 一一对应）、{\"p_values\": [...], \"log2fc\": [...]}（若已有差异结果）。实测缺此字段会被拒：Field required: data_json"
    }
  }
}
act_atac_diff annotations
{
  "title": "ATAC 差异可及性",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_bayesian_design
Advertised by the server during the last successful anonymous check.
Advertised read-only

【贝叶斯自适应设计（qPCR）】 用户要做 qPCR 实验设计、数字孪生 PCR 返回：实验设计方案 （真实算法引擎执行，非大模型生成）

act_bayesian_design input schema
{
  "type": "object",
  "required": [
    "target"
  ],
  "properties": {
    "target": {
      "type": "string",
      "description": "目标基因/模板"
    },
    "constraints": {
      "type": "string",
      "description": "约束条件"
    }
  }
}
act_bayesian_design annotations
{
  "title": "贝叶斯自适应设计（qPCR）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_be_compare
Advertised by the server during the last successful anonymous check.
Advertised read-only

【生物等效性评价】 用户要做 BE 试验的 AUC/Cmax 比较 返回：90%CI 与等效性判定 （真实算法引擎执行，非大模型生成）

act_be_compare input schema
{
  "type": "object",
  "required": [
    "test_auc_list",
    "reference_auc_list"
  ],
  "properties": {
    "test_auc_list": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "受试制剂 AUC"
    },
    "reference_auc_list": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "参比制剂 AUC"
    }
  }
}
act_be_compare annotations
{
  "title": "生物等效性评价",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_bridge_convert
Advertised by the server during the last successful anonymous check.
Advertised read-only

【临床↔基础转化配对】 用户要从临床发现找基础机制，或从机制找临床应用（Bridge） 返回：转化研究假说与实验方案 （真实算法引擎执行，非大模型生成）

act_bridge_convert input schema
{
  "type": "object",
  "required": [
    "finding"
  ],
  "properties": {
    "finding": {
      "type": "string",
      "description": "临床发现/基础发现"
    },
    "direction": {
      "type": "string",
      "description": "clinical2basic 或 basic2clinical"
    }
  }
}
act_bridge_convert annotations
{
  "title": "临床↔基础转化配对",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_calibration
Advertised by the server during the last successful anonymous check.
Advertised read-only

【校准曲线】 用户要评估预测模型的校准度、画校准曲线 返回：校准曲线与 Brier 分数 （真实算法引擎执行，非大模型生成）

act_calibration input schema
{
  "type": "object",
  "required": [
    "labels",
    "scores"
  ],
  "properties": {
    "labels": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "真实标签"
    },
    "n_bins": {
      "type": "integer",
      "description": "分箱数"
    },
    "scores": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "预测概率（0~1）"
    }
  }
}
act_calibration annotations
{
  "title": "校准曲线",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_cell_tool
Advertised by the server during the last successful anonymous check.
Advertised read-only

【细胞实验通用计算】 用户要做 CCK8/划痕/Transwell/克隆形成等细胞实验计算 返回：计算结果 （真实算法引擎执行，非大模型生成）

act_cell_tool input schema
{
  "type": "object",
  "required": [
    "tool_id"
  ],
  "properties": {
    "params": {
      "type": "object",
      "description": "该工具所需参数"
    },
    "tool_id": {
      "type": "string",
      "description": "工具 id，如 cck8/wound-healing/transwell/colony"
    }
  }
}
act_cell_tool annotations
{
  "title": "细胞实验通用计算",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_checklist_check
Advertised by the server during the last successful anonymous check.
Advertised read-only

【报告规范清单核对】 用户问论文符不符合 CONSORT/STROBE 等报告规范 返回：逐条核对结果 （真实算法引擎执行，非大模型生成）

act_checklist_check input schema
{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "论文正文"
    },
    "design_type": {
      "type": "string",
      "description": "研究设计类型"
    }
  }
}
act_checklist_check annotations
{
  "title": "报告规范清单核对",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_chip_peak
Advertised by the server during the last successful anonymous check.
Advertised read-only

【ChIP-seq Peak calling】 用户有 ChIP-seq 要做 peak calling 返回：peak 清单 （真实算法引擎执行，非大模型生成）

act_chip_peak input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "data_json": {
      "type": "object",
      "description": "必填。数据对象（不是字符串）。矩阵形式：{\"matrix\": [[行1各列数值...], [行2...]], \"rows\": [\"基因/特征名\"], \"cols\": [\"样本名\"]}；组学结果另可带 {\"groups\": [\"组A\",\"组A\",\"组B\"...]}（与 cols 一一对应）、{\"p_values\": [...], \"log2fc\": [...]}（若已有差异结果）。实测缺此字段会被拒：Field required: data_json"
    }
  }
}
act_chip_peak annotations
{
  "title": "ChIP-seq Peak calling",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_citation_format
Advertised by the server during the last successful anonymous check.
Advertised read-only

【引文格式化】 用户要把参考文献转成 Vancouver/APA/GB-T 7714 格式 返回：格式化后的引文 （真实算法引擎执行，非大模型生成）

act_citation_format input schema
{
  "type": "object",
  "required": [
    "references"
  ],
  "properties": {
    "style": {
      "type": "string",
      "description": "vancouver/apa/mla/chicago/gbt7714"
    },
    "references": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "参考文献列表"
    }
  }
}
act_citation_format annotations
{
  "title": "引文格式化",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_classification_report
Advertised by the server during the last successful anonymous check.
Advertised read-only

【分类性能报告】 用户要看准确率/敏感度/特异度/PPV/NPV 全套指标 返回：分类指标全套 （真实算法引擎执行，非大模型生成）

act_classification_report input schema
{
  "type": "object",
  "required": [
    "labels",
    "predictions"
  ],
  "properties": {
    "labels": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "真实标签"
    },
    "threshold": {
      "type": "number",
      "description": "判定阈值"
    },
    "predictions": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "预测结果（0/1）"
    }
  }
}
act_classification_report annotations
{
  "title": "分类性能报告",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_cloning_design
Advertised by the server during the last successful anonymous check.
Advertised read-only

【克隆方案设计】 用户要做分子克隆、构建质粒、设计同源臂 返回：克隆方案与引物 （真实算法引擎执行，非大模型生成）

act_cloning_design input schema
{
  "type": "object",
  "required": [
    "insert_seq",
    "vector_seq"
  ],
  "properties": {
    "method": {
      "type": "string",
      "description": "Gibson / Golden Gate / 酶切连接"
    },
    "insert_seq": {
      "type": "string",
      "description": "插入片段序列（≥40bp）"
    },
    "vector_seq": {
      "type": "string",
      "description": "载体序列"
    }
  }
}
act_cloning_design annotations
{
  "title": "克隆方案设计",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_consort_flow
Advertised by the server during the last successful anonymous check.
Advertised read-only

【CONSORT 流程图】 用户有筛选/随机化/失访人数，要画 CONSORT 流程图 返回：CONSORT 流程图 （真实算法引擎执行，非大模型生成）

act_consort_flow input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "title": {
      "type": "string",
      "description": "研究题目"
    },
    "screened": {
      "type": "integer",
      "description": "筛选人数"
    },
    "randomized": {
      "type": "integer",
      "description": "随机化人数"
    },
    "allocated_control": {
      "type": "integer",
      "description": "对照组分配数"
    },
    "excluded_screening": {
      "type": "integer",
      "description": "筛除人数"
    },
    "allocated_intervention": {
      "type": "integer",
      "description": "干预组分配数"
    },
    "lost_to_followup_control": {
      "type": "integer",
      "description": "对照组失访数"
    },
    "lost_to_followup_intervention": {
      "type": "integer",
      "description": "干预组失访数"
    }
  }
}
act_consort_flow annotations
{
  "title": "CONSORT 流程图",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_crf_validate
Advertised by the server during the last successful anonymous check.
Advertised read-only

【CRF 数据校验（SDTM）】 用户问 CRF 数据合不合规、能不能导出 CDISC 返回：校验结果 （真实算法引擎执行，非大模型生成）

act_crf_validate input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "form_id": {
      "type": "integer",
      "description": "表单 id"
    }
  }
}
act_crf_validate annotations
{
  "title": "CRF 数据校验（SDTM）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_data_quick_stats
Advertised by the server during the last successful anonymous check.
Advertised read-only

【数据快速画像】 用户想先看看这份数据长什么样、分布、缺失 返回：描述统计与质量概览 （真实算法引擎执行，非大模型生成）

act_data_quick_stats input schema
{
  "type": "object",
  "required": [
    "file_id"
  ],
  "properties": {
    "file_id": {
      "type": "integer",
      "description": "数据文件 id"
    },
    "study_design": {
      "type": "string",
      "description": "研究设计"
    }
  }
}
act_data_quick_stats annotations
{
  "title": "数据快速画像",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_ddi_check
Advertised by the server during the last successful anonymous check.
Advertised read-only

【药物相互作用检查】 用户问两个药能不能一起用、有没有相互作用 返回：相互作用等级与机制 （真实算法引擎执行，非大模型生成）

act_ddi_check input schema
{
  "type": "object",
  "required": [
    "drug_a",
    "drug_b"
  ],
  "properties": {
    "drug_a": {
      "type": "string",
      "description": "药物 A"
    },
    "drug_b": {
      "type": "string",
      "description": "药物 B"
    }
  }
}
act_ddi_check annotations
{
  "title": "药物相互作用检查",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_decision_followup
Advertised by the server during the last successful anonymous check.
Advertised read-only

【证据追问（多轮）】 用户要对已录入的证据继续追问、做因果判断 返回：追问答复 （真实算法引擎执行，非大模型生成）

act_decision_followup input schema
{
  "type": "object",
  "required": [
    "title",
    "question"
  ],
  "properties": {
    "round": {
      "type": "integer",
      "description": "轮次"
    },
    "title": {
      "type": "string",
      "description": "标题"
    },
    "abstract": {
      "type": "string",
      "description": "摘要"
    },
    "question": {
      "type": "string",
      "description": "追问问题"
    }
  }
}
act_decision_followup annotations
{
  "title": "证据追问（多轮）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_decision_intake
Advertised by the server during the last successful anonymous check.
Advertised read-only

【文献证据分级录入】 用户给一篇文献要按证据等级结构化拆解（Decision OS） 返回：结构化证据卡 （真实算法引擎执行，非大模型生成）

act_decision_intake input schema
{
  "type": "object",
  "required": [
    "title"
  ],
  "properties": {
    "doi": {
      "type": "string",
      "description": "DOI"
    },
    "title": {
      "type": "string",
      "description": "标题"
    },
    "abstract": {
      "type": "string",
      "description": "摘要"
    },
    "literature_type": {
      "type": "string",
      "description": "文献类型"
    }
  }
}
act_decision_intake annotations
{
  "title": "文献证据分级录入",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_decision_report
Advertised by the server during the last successful anonymous check.
Advertised read-only

【证据报告叙述】 用户要把证据卡生成可读报告 返回：证据报告正文 （真实算法引擎执行，非大模型生成）

act_decision_report input schema
{
  "type": "object",
  "required": [
    "result"
  ],
  "properties": {
    "lang": {
      "enum": [
        "zh",
        "en"
      ],
      "type": "string",
      "description": "可选。报告语言：zh（默认，中文）或 en（英文）。其他值按 zh 处理。"
    },
    "result": {
      "type": "object",
      "description": "必填。上一次 act_decision_intake / act_decision_followup 返回的 result 对象，原样传入即可（内含 causality / drug_stage / evidence_chain 等字段）。实测缺此字段返回：缺少决策结果 result"
    }
  }
}
act_decision_report annotations
{
  "title": "证据报告叙述",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_deg_analyze
Advertised by the server during the last successful anonymous check.
Advertised read-only

【差异表达分析】 用户有表达矩阵要做差异基因分析、火山图 返回：差异基因清单 （真实算法引擎执行，非大模型生成）

act_deg_analyze input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "group_a": {
      "type": "string",
      "description": "A 组样本表达（CSV）"
    },
    "group_b": {
      "type": "string",
      "description": "B 组样本表达（CSV）"
    },
    "gene_names": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "基因名列表"
    },
    "pval_threshold": {
      "type": "number",
      "description": "P 阈值"
    },
    "log2fc_threshold": {
      "type": "number",
      "description": "log2FC 阈值"
    }
  }
}
act_deg_analyze annotations
{
  "title": "差异表达分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_delong
Advertised by the server during the last successful anonymous check.
Advertised read-only

【两条 ROC 的 AUC 比较（DeLong）】 用户有两个指标的 AUC，要比较哪个更好、差异有没有统计学意义 返回：两 AUC 及差值 P 值 （真实算法引擎执行，非大模型生成）

act_delong input schema
{
  "type": "object",
  "required": [
    "labels",
    "scores1",
    "scores2"
  ],
  "properties": {
    "labels": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "真实标签 0/1"
    },
    "scores1": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "指标 1 的分数"
    },
    "scores2": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "指标 2 的分数"
    }
  }
}
act_delong annotations
{
  "title": "两条 ROC 的 AUC 比较（DeLong）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_design_context
Advertised by the server during the last successful anonymous check.
Advertised read-only

【取某一步的上下文】 要基于前序步骤（PICO / 设计类型 / 研究对象）起草某一步内容时，先取上下文，避免重复问用户已经填过的信息 返回：该步骤可用的前序上下文（pico / design_type / population / topic） （真实算法引擎执行，非大模型生成）

act_design_context input schema
{
  "type": "object",
  "required": [
    "project_id",
    "step"
  ],
  "properties": {
    "step": {
      "type": "integer",
      "description": "要看哪一步的上下文（数据编号 1-11）"
    },
    "project_id": {
      "type": "integer",
      "description": "课题 id"
    }
  }
}
act_design_context annotations
{
  "title": "取某一步的上下文",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_design_gate_rules
Advertised by the server during the last successful anonymous check.
Advertised read-only

【方案设计闸门规则】 用户问「为什么这步不让我过」「方案设计要满足什么条件」「哪些是硬性要求」，或助手要解释某一步被拦的原因时先读它，确保解释与平台规则一致（不靠自己编） 返回：每步是否有硬闸门、三道跨步闸门 G1/G2/G3 的原文规则 （真实算法引擎执行，非大模型生成）

act_design_gate_rules input schema
{
  "type": "object",
  "required": [],
  "properties": {}
}
act_design_gate_rules annotations
{
  "title": "方案设计闸门规则",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_design_guide
Advertised by the server during the last successful anonymous check.
Advertised read-only

【研究设计向导】 用户不知道自己的问题该用什么研究设计、要选方案 返回：推荐研究设计与理由 （真实算法引擎执行，非大模型生成）

act_design_guide input schema
{
  "type": "object",
  "required": [
    "pico"
  ],
  "properties": {
    "pico": {
      "type": "string",
      "description": "研究问题/PICO 描述"
    },
    "feasibility": {
      "type": "string",
      "description": "可行性条件（病例量、周期、经费）"
    }
  }
}
act_design_guide annotations
{
  "title": "研究设计向导",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_design_sample_size
Advertised by the server during the last successful anonymous check.
Advertised read-only

【样本量计算（设计口径）】 用户在设计阶段要算样本量、问要做多少例 返回：每组例数与合计 （真实算法引擎执行，非大模型生成）

act_design_sample_size input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "sd": {
      "type": "number",
      "description": "标准差"
    },
    "alpha": {
      "type": "number",
      "description": "显著性水平，默认 0.05"
    },
    "power": {
      "type": "number",
      "description": "把握度，默认 0.8"
    },
    "effect": {
      "type": "number",
      "description": "预期效应量/差值"
    },
    "dropout": {
      "type": "number",
      "description": "脱落率"
    },
    "sample_type": {
      "type": "string",
      "description": "计算类型：两组均数/两组率/相关/生存"
    }
  }
}
act_design_sample_size annotations
{
  "title": "样本量计算（设计口径）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_dose_convert_pharm
Advertised by the server during the last successful anonymous check.
Advertised read-only

【种属剂量换算】 用户要把动物剂量换算成人体剂量 返回：换算后剂量与依据 （真实算法引擎执行，非大模型生成）

act_dose_convert_pharm input schema
{
  "type": "object",
  "required": [
    "source_species",
    "target_species",
    "source_dose"
  ],
  "properties": {
    "source_dose": {
      "type": "number",
      "description": "来源剂量"
    },
    "source_species": {
      "type": "string",
      "description": "来源物种"
    },
    "target_species": {
      "type": "string",
      "description": "目标物种"
    }
  }
}
act_dose_convert_pharm annotations
{
  "title": "种属剂量换算",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_dunn
Advertised by the server during the last successful anonymous check.
Advertised read-only

【多组非参数两两比较（Dunn）】 用户做了 Kruskal-Wallis 后要多组两两比较 返回：两两比较 P 值 （真实算法引擎执行，非大模型生成）

act_dunn input schema
{
  "type": "object",
  "required": [
    "groups"
  ],
  "properties": {
    "groups": {
      "type": "object",
      "description": "{组名: [数值...]}"
    }
  }
}
act_dunn annotations
{
  "title": "多组非参数两两比较（Dunn）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_enrich
Advertised by the server during the last successful anonymous check.
Advertised read-only

【通路富集（GO/KEGG）】 用户有一批基因要做 GO/KEGG 富集、找通路 返回：富集通路与 P 值 （真实算法引擎执行，非大模型生成）

act_enrich input schema
{
  "type": "object",
  "required": [
    "gene_list"
  ],
  "properties": {
    "db_filter": {
      "type": "string",
      "description": "数据库：GO_BP/GO_CC/GO_MF/KEGG"
    },
    "gene_list": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "基因列表"
    },
    "project_id": {
      "type": "integer",
      "description": "项目 id"
    }
  }
}
act_enrich annotations
{
  "title": "通路富集（GO/KEGG）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_fcs_cluster
Advertised by the server during the last successful anonymous check.
Advertised read-only

【流式细胞聚类】 用户要对流式数据做无监督聚类分群 返回：细胞群与比例 （真实算法引擎执行，非大模型生成）

act_fcs_cluster input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "events": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "事件数据"
    },
    "grid_size": {
      "type": "integer",
      "description": "网格大小"
    },
    "n_clusters": {
      "type": "integer",
      "description": "聚类数"
    }
  }
}
act_fcs_cluster annotations
{
  "title": "流式细胞聚类",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_fcs_gate
Advertised by the server during the last successful anonymous check.
Advertised read-only

【流式门控分析】 用户有流式数据要做圈门 返回：门控比例 （真实算法引擎执行，非大模型生成）

act_fcs_gate input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "events": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "事件数据"
    },
    "method": {
      "type": "string",
      "description": "门控方法"
    },
    "params": {
      "type": "object",
      "description": "门控参数"
    }
  }
}
act_fcs_gate annotations
{
  "title": "流式门控分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_fibrosis_stage
Advertised by the server during the last successful anonymous check.
Advertised read-only

【纤维化分期】 用户要做肝纤维化分期（Ishak/METAVIR 等） 返回：分期结论与解读 （真实算法引擎执行，非大模型生成）

act_fibrosis_stage input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "stage": {
      "type": "integer",
      "description": "分期数"
    },
    "method": {
      "type": "string",
      "description": "分期体系：ishak/metavir/nas"
    }
  }
}
act_fibrosis_stage annotations
{
  "title": "纤维化分期",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_figure_legend
Advertised by the server during the last successful anonymous check.
Advertised read-only

【图注生成】 用户有图要写图注、Figure legend 返回：图注文本 （真实算法引擎执行，非大模型生成）

act_figure_legend input schema
{
  "type": "object",
  "required": [
    "chart_type"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "图的背景与数据"
    },
    "chart_type": {
      "type": "string",
      "description": "图类型"
    }
  }
}
act_figure_legend annotations
{
  "title": "图注生成",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_file_columns
Advertised by the server during the last successful anonymous check.
Advertised read-only

【读取数据列名】 用户要知道某个数据文件有哪些变量列（做 Table One / 建模前必看） 返回：列名与类型 （真实算法引擎执行，非大模型生成）

act_file_columns input schema
{
  "type": "object",
  "required": [
    "file_id"
  ],
  "properties": {
    "file_id": {
      "type": "integer",
      "description": "数据文件 id"
    }
  }
}
act_file_columns annotations
{
  "title": "读取数据列名",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_forest_chart
Advertised by the server during the last successful anonymous check.
Advertised read-only

【森林图】 用户有 HR/OR/RR 和置信区间，要画森林图 返回：森林图（矢量） （真实算法引擎执行，非大模型生成）

act_forest_chart input schema
{
  "type": "object",
  "required": [
    "data"
  ],
  "properties": {
    "data": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "每项 {name, estimate, ci_lower, ci_upper}"
    },
    "title": {
      "type": "string",
      "description": "图标题"
    },
    "x_label": {
      "type": "string",
      "description": "X 轴标签"
    }
  }
}
act_forest_chart annotations
{
  "title": "森林图",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_gene_pathway
Advertised by the server during the last successful anonymous check.
Advertised read-only

【基因-通路-疾病网络】 用户要从一批基因找通路、疾病、药物关联 返回：通路/疾病/药物关联 （真实算法引擎执行，非大模型生成）

act_gene_pathway input schema
{
  "type": "object",
  "required": [
    "genes"
  ],
  "properties": {
    "genes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "基因列表"
    }
  }
}
act_gene_pathway annotations
{
  "title": "基因-通路-疾病网络",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_gene_search
Advertised by the server during the last successful anonymous check.
Advertised read-only

【基因信息检索】 用户问某个基因是干什么的、别名、功能 返回：基因信息 （真实算法引擎执行，非大模型生成）

act_gene_search input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "基因名/关键词"
    }
  }
}
act_gene_search annotations
{
  "title": "基因信息检索",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_geo_pipeline
Advertised by the server during the last successful anonymous check.
Advertised read-only

【GEO 数据全流程】 用户给 GEO 编号要做差异分析、富集、免疫浸润全流程 返回：差异基因、富集结果 （真实算法引擎执行，非大模型生成）

act_geo_pipeline input schema
{
  "type": "object",
  "required": [
    "geo_id"
  ],
  "properties": {
    "geo_id": {
      "type": "string",
      "description": "GEO 数据集编号，如 GSE12345"
    },
    "species": {
      "type": "string",
      "description": "物种：human/mouse"
    },
    "pval_cutoff": {
      "type": "number",
      "description": "P 阈值"
    },
    "logfc_cutoff": {
      "type": "number",
      "description": "logFC 阈值"
    }
  }
}
act_geo_pipeline annotations
{
  "title": "GEO 数据全流程",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_gleason
Advertised by the server during the last successful anonymous check.
Advertised read-only

【Gleason 分级分组】 用户问前列腺癌 Gleason 评分对应哪个 Grade Group 返回：Grade Group 与风险分层 （真实算法引擎执行，非大模型生成）

act_gleason input schema
{
  "type": "object",
  "required": [
    "primary_grade",
    "secondary_grade"
  ],
  "properties": {
    "primary_grade": {
      "type": "integer",
      "description": "主要分级 1-5"
    },
    "secondary_grade": {
      "type": "integer",
      "description": "次要分级 1-5"
    }
  }
}
act_gleason annotations
{
  "title": "Gleason 分级分组",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_ic50_fit
Advertised by the server during the last successful anonymous check.
Advertised read-only

【IC50 曲线拟合】 用户有药物浓度和抑制率要算 IC50 返回：IC50 值与 95%CI （真实算法引擎执行，非大模型生成）

act_ic50_fit input schema
{
  "type": "object",
  "required": [
    "concentrations",
    "responses"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "拟合模型：4PL/3PL"
    },
    "direction": {
      "type": "string",
      "description": "inhibition 或 activation"
    },
    "responses": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "响应/抑制率"
    },
    "concentrations": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "浓度序列"
    }
  }
}
act_ic50_fit annotations
{
  "title": "IC50 曲线拟合",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_ihc_score
Advertised by the server during the last successful anonymous check.
Advertised read-only

【IHC 免疫组化评分】 用户有 IHC 染色结果要算 H-score/Allred/阳性率 返回：H-score / Allred / 阳性率 （真实算法引擎执行，非大模型生成）

act_ihc_score input schema
{
  "type": "object",
  "required": [
    "stain_type"
  ],
  "properties": {
    "stain_type": {
      "type": "string",
      "description": "染色类型"
    },
    "intensity_0_pct": {
      "type": "number",
      "description": "0 级占比(%)"
    },
    "intensity_1_pct": {
      "type": "number",
      "description": "1+ 占比(%)"
    },
    "intensity_2_pct": {
      "type": "number",
      "description": "2+ 占比(%)"
    },
    "intensity_3_pct": {
      "type": "number",
      "description": "3+ 占比(%)"
    }
  }
}
act_ihc_score annotations
{
  "title": "IHC 免疫组化评分",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_iptw
Advertised by the server during the last successful anonymous check.
Advertised read-only

【IPTW 逆概率加权】 用户要做倾向评分加权分析 返回：权重与加权后效应 （真实算法引擎执行，非大模型生成）

act_iptw input schema
{
  "type": "object",
  "required": [
    "propensity_scores",
    "treatment"
  ],
  "properties": {
    "treatment": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "处理分组 0/1"
    },
    "propensity_scores": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "倾向评分"
    }
  }
}
act_iptw annotations
{
  "title": "IPTW 逆概率加权",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_journal_recommend_v3
Advertised by the server during the last successful anonymous check.
Advertised read-only

【智能选刊 V3】 用户要按题目摘要推荐期刊、冲/稳/保三档 返回：候选期刊与三档策略 （真实算法引擎执行，非大模型生成）

act_journal_recommend_v3 input schema
{
  "type": "object",
  "required": [
    "title"
  ],
  "properties": {
    "title": {
      "type": "string",
      "description": "论文标题"
    },
    "design": {
      "type": "string",
      "description": "研究设计"
    },
    "abstract": {
      "type": "string",
      "description": "摘要"
    },
    "keywords": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "关键词"
    },
    "sample_size": {
      "type": "integer",
      "description": "样本量"
    },
    "target_tier": {
      "type": "string",
      "description": "目标档次"
    }
  }
}
act_journal_recommend_v3 annotations
{
  "title": "智能选刊 V3",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_km_curve
Advertised by the server during the last successful anonymous check.
Advertised read-only

【Kaplan-Meier 曲线】 用户只要 KM 曲线和中位生存，不做多因素 返回：KM 曲线与中位生存 （真实算法引擎执行，非大模型生成）

act_km_curve input schema
{
  "type": "object",
  "required": [
    "times",
    "events"
  ],
  "properties": {
    "times": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "随访时间"
    },
    "events": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "事件 0/1"
    },
    "groups": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "分组"
    }
  }
}
act_km_curve annotations
{
  "title": "Kaplan-Meier 曲线",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_lit_search
Advertised by the server during the last successful anonymous check.
Advertised read-only

【文献检索（站内 153 万篇 PMC）】 用户要找文献、找证据、看研究现状 返回：文献列表（含 PMCID） （真实算法引擎执行，非大模型生成）

act_lit_search input schema
{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "检索词（英文效果更好）"
    },
    "limit": {
      "type": "integer",
      "description": "返回条数"
    }
  }
}
act_lit_search annotations
{
  "title": "文献检索（站内 153 万篇 PMC）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_lit_verify_citations
Advertised by the server during the last successful anonymous check.
Advertised read-only

【引文真实性核验】 用户担心参考文献是编的、要核验引用真伪 返回：逐条核验结果 （真实算法引擎执行，非大模型生成）

act_lit_verify_citations input schema
{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "含引用的正文"
    },
    "topic": {
      "type": "string",
      "description": "主题"
    }
  }
}
act_lit_verify_citations annotations
{
  "title": "引文真实性核验",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_literature_overlap
Advertised by the server during the last successful anonymous check.
Advertised read-only

【文字重合度自查】 用户问这段文字和我自己以前的文章重不重（查重） 返回：重合度与相似文献 （真实算法引擎执行，非大模型生成）

act_literature_overlap input schema
{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "待查文本"
    },
    "top_n": {
      "type": "integer",
      "description": "返回条数"
    }
  }
}
act_literature_overlap annotations
{
  "title": "文字重合度自查",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_lmm_formula
Advertised by the server during the last successful anonymous check.
Advertised read-only

【线性混合模型（纵向/重复测量，公式模式）】 同一受试者在多个时间点被反复测量（治疗前后各测一次、多次随访、多个时间点重复观察、每人测三四次、每例随访若干次），要比较各组随时间的变化趋势、要看组与时间的交互；也是重复测量方差分析的现代替代（允许缺失、不必球形检验） 返回：固定效应系数/SE/Wald z/P/95%CI（按真实变量名，不是 X1/X2）、各项整体检验 omnibus、交互项检验、primary_test、ICC、方差成分、n_subjects/n_obs、组间例数、缺失与收敛告警 （真实算法引擎执行，非大模型生成）

act_lmm_formula input schema
{
  "type": "object",
  "required": [
    "data",
    "formula",
    "subject"
  ],
  "properties": {
    "data": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "长格式数据：每行一次观测 [{受试者ID, 分组, 时点, 结局}, ...]；也接受列式 {列名: [值, ...]}。注意必须是**长表**（每行一次测量），不是每人一行多列"
    },
    "reml": {
      "type": "boolean",
      "description": "默认 true（REML）"
    },
    "formula": {
      "type": "string",
      "description": "R 风格公式，如 '收缩压 ~ 分组 * 时点'（组×时间交互）；左端=结局"
    },
    "subject": {
      "type": "string",
      "description": "受试者/病案号列名（随机截距的分组依据）"
    },
    "reference": {
      "type": "object",
      "description": "参照水平，如 {\"分组\": \"对照组\"} —— 报告表里「与对照组相比」必须是它"
    },
    "re_formula": {
      "type": "string",
      "description": "随机效应，默认 '1'（随机截距）；随机斜率用 '1 + 时点'"
    },
    "categorical": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "显式声明哪些列按分类处理（如 [\"分组\"]）；数值编码的 0/1 分组必须声明，否则会被当连续变量"
    },
    "time_values": {
      "type": "object",
      "description": "把字符串时点映射成数值以估线性趋势，如 {\"时点\": {\"基线\":0,\"4周\":1,\"12周\":2}}"
    }
  }
}
act_lmm_formula annotations
{
  "title": "线性混合模型（纵向/重复测量，公式模式）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_meta_egger
Advertised by the server during the last successful anonymous check.
Advertised read-only

【Meta 发表偏倚（Egger）】 用户做 Meta 分析要检验发表偏倚、画漏斗图 返回：Egger 检验 P 与截距 （真实算法引擎执行，非大模型生成）

act_meta_egger input schema
{
  "type": "object",
  "required": [
    "log_or",
    "se_log_or"
  ],
  "properties": {
    "log_or": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "各研究 logOR"
    },
    "se_log_or": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "各研究 SE"
    }
  }
}
act_meta_egger annotations
{
  "title": "Meta 发表偏倚（Egger）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_metabo_enrichment
Advertised by the server during the last successful anonymous check.
Advertised read-only

【代谢物通路富集】 用户有一批差异代谢物要找通路 返回：代谢通路富集 （真实算法引擎执行，非大模型生成）

act_metabo_enrichment input schema
{
  "type": "object",
  "required": [
    "metabolites"
  ],
  "properties": {
    "metabolites": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "代谢物列表"
    },
    "fdr_threshold": {
      "type": "number",
      "description": "FDR 阈值"
    }
  }
}
act_metabo_enrichment annotations
{
  "title": "代谢物通路富集",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_metabo_heatmap
Advertised by the server during the last successful anonymous check.
Advertised read-only

【代谢组热图】 用户要画代谢物聚类热图 返回：聚类热图 （真实算法引擎执行，非大模型生成）

act_metabo_heatmap input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "data_json": {
      "type": "object",
      "description": "必填。数据对象（不是字符串）。矩阵形式：{\"matrix\": [[行1各列数值...], [行2...]], \"rows\": [\"基因/特征名\"], \"cols\": [\"样本名\"]}；组学结果另可带 {\"groups\": [\"组A\",\"组A\",\"组B\"...]}（与 cols 一一对应）、{\"p_values\": [...], \"log2fc\": [...]}（若已有差异结果）。实测缺此字段会被拒：Field required: data_json"
    }
  }
}
act_metabo_heatmap annotations
{
  "title": "代谢组热图",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_metabo_pca
Advertised by the server during the last successful anonymous check.
Advertised read-only

【代谢组 PCA】 用户要看样本分组趋势、有没有离群 返回：PCA 得分与解释度 （真实算法引擎执行，非大模型生成）

act_metabo_pca input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "groups": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "分组标签"
    },
    "data_json": {
      "type": "object",
      "description": "代谢物矩阵"
    }
  }
}
act_metabo_pca annotations
{
  "title": "代谢组 PCA",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_metabo_plsda
Advertised by the server during the last successful anonymous check.
Advertised read-only

【代谢组 PLS-DA】 用户要做有监督判别分析、找差异代谢物 返回：PLS-DA 模型与 VIP （真实算法引擎执行，非大模型生成）

act_metabo_plsda input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "groups": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "分组标签"
    },
    "data_json": {
      "type": "object",
      "description": "代谢物矩阵"
    }
  }
}
act_metabo_plsda annotations
{
  "title": "代谢组 PLS-DA",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_metabo_volcano
Advertised by the server during the last successful anonymous check.
Advertised read-only

【代谢组火山图】 用户要画代谢物火山图 返回：火山图 （真实算法引擎执行，非大模型生成）

act_metabo_volcano input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "data_json": {
      "type": "object",
      "description": "必填。数据对象（不是字符串）。矩阵形式：{\"matrix\": [[行1各列数值...], [行2...]], \"rows\": [\"基因/特征名\"], \"cols\": [\"样本名\"]}；组学结果另可带 {\"groups\": [\"组A\",\"组A\",\"组B\"...]}（与 cols 一一对应）、{\"p_values\": [...], \"log2fc\": [...]}（若已有差异结果）。实测缺此字段会被拒：Field required: data_json"
    }
  }
}
act_metabo_volcano annotations
{
  "title": "代谢组火山图",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_mif_phenotype
Advertised by the server during the last successful anonymous check.
Advertised read-only

【多重免疫荧光表型】 用户有多少免疫荧光标记要定细胞表型 返回：细胞亚群表型与比例 （真实算法引擎执行，非大模型生成）

act_mif_phenotype input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "cd3_pos": {
      "type": "number",
      "description": "CD3+ 数"
    },
    "cd8_pos": {
      "type": "number",
      "description": "CD8+ 数"
    },
    "foxp3_pos": {
      "type": "number",
      "description": "FoxP3+ 数"
    },
    "pd_l1_pos": {
      "type": "number",
      "description": "PD-L1+ 数"
    }
  }
}
act_mif_phenotype annotations
{
  "title": "多重免疫荧光表型",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_ml_nomogram
Advertised by the server during the last successful anonymous check.
Advertised read-only

【列线图 Nomogram】 用户要把 Logistic/Cox 模型做成列线图 返回：列线图 SVG （真实算法引擎执行，非大模型生成）

act_ml_nomogram input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "csv_data": {
      "type": "string",
      "description": "CSV 文本"
    }
  }
}
act_ml_nomogram annotations
{
  "title": "列线图 Nomogram",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_ml_parse
Advertised by the server during the last successful anonymous check.
Advertised read-only

【数据解析与列类型识别】 用户贴了一段 CSV/表格，要先看数据长什么样、每列是什么类型 返回：行列数、列类型、缺失情况 （真实算法引擎执行，非大模型生成）

act_ml_parse input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "csv_data": {
      "type": "string",
      "description": "CSV 文本"
    }
  }
}
act_ml_parse annotations
{
  "title": "数据解析与列类型识别",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_ml_psi
Advertised by the server during the last successful anonymous check.
Advertised read-only

【模型稳定性 PSI】 用户要评估模型换数据后稳不稳（PSI） 返回：PSI 值与稳定性判断 （真实算法引擎执行，非大模型生成）

act_ml_psi input schema
{
  "type": "object",
  "required": [
    "expected_probs",
    "observed_probs"
  ],
  "properties": {
    "n_bins": {
      "type": "integer",
      "description": "分箱数"
    },
    "expected_probs": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "开发集概率"
    },
    "observed_probs": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "验证集概率"
    }
  }
}
act_ml_psi annotations
{
  "title": "模型稳定性 PSI",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_ml_shap
Advertised by the server during the last successful anonymous check.
Advertised read-only

【SHAP 单样本解释】 用户要解释某个病人为什么被判高风险 返回：SHAP 贡献图 （真实算法引擎执行，非大模型生成）

act_ml_shap input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "csv_data": {
      "type": "string",
      "description": "CSV 文本"
    },
    "model_type": {
      "type": "string",
      "description": "模型类型"
    },
    "sample_index": {
      "type": "integer",
      "description": "样本序号"
    }
  }
}
act_ml_shap annotations
{
  "title": "SHAP 单样本解释",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_nca_analyze
Advertised by the server during the last successful anonymous check.
Advertised read-only

【NCA 非房室药代分析】 用户有血药浓度-时间数据要算 AUC/Cmax/T1/2 返回：AUC/Cmax/Tmax/T1/2/CL/Vd （真实算法引擎执行，非大模型生成）

act_nca_analyze input schema
{
  "type": "object",
  "required": [
    "time_points",
    "concentrations"
  ],
  "properties": {
    "dose": {
      "type": "number",
      "description": "给药剂量"
    },
    "dose_unit": {
      "type": "string",
      "description": "剂量单位，如 mg/kg"
    },
    "time_points": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "时间点"
    },
    "concentrations": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "浓度"
    }
  }
}
act_nca_analyze annotations
{
  "title": "NCA 非房室药代分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_nuclei_segment
Advertised by the server during the last successful anonymous check.
Advertised read-only

【细胞核分割与计数】 用户要算切片里的细胞密度/阳性率 返回：分割统计结果 （真实算法引擎执行，非大模型生成）

act_nuclei_segment input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "stain_type": {
      "type": "string",
      "description": "染色类型"
    },
    "cell_density": {
      "type": "number",
      "description": "细胞密度"
    },
    "positive_rate": {
      "type": "number",
      "description": "阳性率"
    }
  }
}
act_nuclei_segment annotations
{
  "title": "细胞核分割与计数",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_omics_integrate
Advertised by the server during the last successful anonymous check.
Advertised read-only

【多组学整合】 用户要把 mRNA/蛋白/代谢物一起整合分析 返回：多组学关联结果 （真实算法引擎执行，非大模型生成）

act_omics_integrate input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "mrna": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "mRNA 列表"
    },
    "protein": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "蛋白列表"
    },
    "metabolite": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "代谢物列表"
    },
    "pathway_map": {
      "type": "string",
      "description": "通路映射方式"
    }
  }
}
act_omics_integrate annotations
{
  "title": "多组学整合",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_permutation_test
Advertised by the server during the last successful anonymous check.
Advertised read-only

【置换检验】 数据不满足 t 检验前提、样本很小、要做非参数精确置换检验 返回：置换 P 值 （真实算法引擎执行，非大模型生成）

act_permutation_test input schema
{
  "type": "object",
  "required": [
    "group1",
    "group2"
  ],
  "properties": {
    "group1": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "第一组数值"
    },
    "group2": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "第二组数值"
    },
    "n_perm": {
      "type": "integer",
      "description": "置换次数，默认 10000"
    }
  }
}
act_permutation_test annotations
{
  "title": "置换检验",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_pico_refine
Advertised by the server during the last successful anonymous check.
Advertised read-only

【PICO 精炼】 用户给了研究问题，要拆成规范的 PICO 返回：结构化 PICO （真实算法引擎执行，非大模型生成）

act_pico_refine input schema
{
  "type": "object",
  "required": [
    "pico"
  ],
  "properties": {
    "pico": {
      "type": "object",
      "description": "结构化 PICO，如 {\"P\":\"ICU 脓毒症患者\",\"I\":\"乳酸清除率\",\"C\":\"常规\",\"O\":\"28天病死率\"}"
    }
  }
}
act_pico_refine annotations
{
  "title": "PICO 精炼",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_pkpd_eval
Advertised by the server during the last successful anonymous check.
Advertised read-only

【PK/PD 评估】 用户要做药代药效评估、剂量推算 返回：PK/PD 评估结果 （真实算法引擎执行，非大模型生成）

act_pkpd_eval input schema
{
  "type": "object",
  "required": [
    "drug_name"
  ],
  "properties": {
    "drug_name": {
      "type": "string",
      "description": "药物名称"
    },
    "pk_params": {
      "type": "object",
      "description": "药代参数"
    }
  }
}
act_pkpd_eval annotations
{
  "title": "PK/PD 评估",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_pkpd_simulate
Advertised by the server during the last successful anonymous check.
Advertised read-only

【PK/PD 模拟】 用户要模拟给药方案的浓度-效应过程 返回：模拟曲线与参数 （真实算法引擎执行，非大模型生成）

act_pkpd_simulate input schema
{
  "type": "object",
  "required": [
    "drug_name"
  ],
  "properties": {
    "drug_name": {
      "type": "string",
      "description": "药物名"
    },
    "pd_params": {
      "type": "object",
      "description": "药效参数"
    },
    "pk_params": {
      "type": "object",
      "description": "药代参数"
    }
  }
}
act_pkpd_simulate annotations
{
  "title": "PK/PD 模拟",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_ppi_network
Advertised by the server during the last successful anonymous check.
Advertised read-only

【蛋白互作网络】 用户有一批蛋白要做 PPI 网络、找 hub 返回：互作网络与 hub 蛋白 （真实算法引擎执行，非大模型生成）

act_ppi_network input schema
{
  "type": "object",
  "required": [
    "protein_list"
  ],
  "properties": {
    "species": {
      "type": "string",
      "description": "物种：human/mouse"
    },
    "protein_list": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "蛋白/基因列表"
    },
    "confidence_threshold": {
      "type": "number",
      "description": "置信度阈值"
    }
  }
}
act_ppi_network annotations
{
  "title": "蛋白互作网络",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_primer_design
Advertised by the server during the last successful anonymous check.
Advertised read-only

【PCR 引物设计】 用户给了 DNA 序列或基因，要设计 PCR 引物 返回：候选引物对与 Tm/GC （真实算法引擎执行，非大模型生成）

act_primer_design input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "gene": {
      "type": "string",
      "description": "基因名（无序列时用）"
    },
    "sequence": {
      "type": "string",
      "description": "模板 DNA 序列"
    }
  }
}
act_primer_design annotations
{
  "title": "PCR 引物设计",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_primer_tm
Advertised by the server during the last successful anonymous check.
Advertised read-only

【引物 Tm 计算】 用户给了引物序列要算 Tm、GC、二聚体 返回：Tm、GC、二聚体 （真实算法引擎执行，非大模型生成）

act_primer_tm input schema
{
  "type": "object",
  "required": [
    "sequence"
  ],
  "properties": {
    "sequence": {
      "type": "string",
      "description": "引物序列"
    }
  }
}
act_primer_tm annotations
{
  "title": "引物 Tm 计算",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_prisma_flow
Advertised by the server during the last successful anonymous check.
Advertised read-only

【PRISMA 流程图】 用户做系统评价/Meta 分析，要画文献筛选流程图 返回：PRISMA 流程图 （真实算法引擎执行，非大模型生成）

act_prisma_flow input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "title": {
      "type": "string",
      "description": "研究题目"
    },
    "records_screened": {
      "type": "integer",
      "description": "筛读记录数"
    },
    "studies_included": {
      "type": "integer",
      "description": "最终纳入研究数"
    },
    "records_identified": {
      "type": "integer",
      "description": "检索记录数"
    }
  }
}
act_prisma_flow annotations
{
  "title": "PRISMA 流程图",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_protein_digest
Advertised by the server during the last successful anonymous check.
Advertised read-only

【蛋白酶解模拟】 用户要选酶做质谱前处理、算肽段 返回：肽段清单 （真实算法引擎执行，非大模型生成）

act_protein_digest input schema
{
  "type": "object",
  "required": [
    "sequence"
  ],
  "properties": {
    "enzymes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "酶：Trypsin/Lys-C"
    },
    "sequence": {
      "type": "string",
      "description": "蛋白序列"
    }
  }
}
act_protein_digest annotations
{
  "title": "蛋白酶解模拟",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_protein_enrichment
Advertised by the server during the last successful anonymous check.
Advertised read-only

【蛋白富集分析】 用户有一批蛋白要做 GO/KEGG 富集 返回：富集通路 （真实算法引擎执行，非大模型生成）

act_protein_enrichment input schema
{
  "type": "object",
  "required": [
    "protein_list"
  ],
  "properties": {
    "species": {
      "type": "string",
      "description": "物种"
    },
    "protein_list": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "蛋白列表"
    },
    "enrichment_type": {
      "type": "string",
      "description": "GO/KEGG/Reactome"
    }
  }
}
act_protein_enrichment annotations
{
  "title": "蛋白富集分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_protein_physchem
Advertised by the server during the last successful anonymous check.
Advertised read-only

【蛋白理化性质】 用户给蛋白序列要算分子量/等电点/疏水性 返回：MW/pI/GRAVY 等 （真实算法引擎执行，非大模型生成）

act_protein_physchem input schema
{
  "type": "object",
  "required": [
    "sequence"
  ],
  "properties": {
    "sequence": {
      "type": "string",
      "description": "蛋白序列"
    },
    "protein_name": {
      "type": "string",
      "description": "蛋白名"
    }
  }
}
act_protein_physchem annotations
{
  "title": "蛋白理化性质",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_protein_ptm
Advertised by the server during the last successful anonymous check.
Advertised read-only

【翻译后修饰分析】 用户要预测磷酸化/糖基化等修饰位点 返回：修饰位点预测 （真实算法引擎执行，非大模型生成）

act_protein_ptm input schema
{
  "type": "object",
  "required": [
    "sequence"
  ],
  "properties": {
    "sequence": {
      "type": "string",
      "description": "蛋白序列"
    },
    "modifications": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "修饰类型：phosphorylation/glycosylation"
    }
  }
}
act_protein_ptm annotations
{
  "title": "翻译后修饰分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_psm_match
Advertised by the server during the last successful anonymous check.
Advertised read-only

【倾向性评分匹配 PSM】 用户要做 PSM、倾向评分匹配、1:1 匹配基线 返回：匹配后样本与均衡性 （真实算法引擎执行，非大模型生成）

act_psm_match input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "data": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "样本数据"
    },
    "ratio": {
      "type": "number",
      "description": "匹配比例，默认 1"
    },
    "treatment": {
      "type": "string",
      "description": "处理变量列名"
    },
    "covariates": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "协变量列名"
    }
  }
}
act_psm_match annotations
{
  "title": "倾向性评分匹配 PSM",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_pubmed_search
Advertised by the server during the last successful anonymous check.
Advertised read-only

【PubMed 检索】 用户要查 PubMed、要最新文献 返回：PubMed 文献列表 （真实算法引擎执行，非大模型生成）

act_pubmed_search input schema
{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "检索式（英文）"
    },
    "year_start": {
      "type": "integer",
      "description": "起始年份"
    },
    "max_results": {
      "type": "integer",
      "description": "条数"
    }
  }
}
act_pubmed_search annotations
{
  "title": "PubMed 检索",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_qpcr_ddct
Advertised by the server during the last successful anonymous check.
Advertised read-only

【qPCR 相对表达量（2^-ΔΔCt）】 用户给出目的基因与内参基因的 Ct 值（对照组/处理组各若干重复），要算 ΔCt、ΔΔCt、2^-ΔΔCt 相对表达量或倍数、并做组间检验时，必须走这个动作。🔴 严禁自己心算 ΔΔCt 与倍数：校准必须用**对照组 ΔCt 的均值**（不是某一个对照样本的值，用了单样本会整体偏高/偏低）；且统计检验要由引擎判断（组内零方差时 Welch t 会给出虚高的 P 值，引擎会改用 Mann-Whitney）。返回里 stat_method / tested_variable 必须如实转述。Ct 值用逗号分隔，两组与各自内参一一对应。 返回：fc（2^-ΔΔCt 相对倍数，已按对照组 ΔCt 均值校准）、fold_values、p_value、stat_method（welch_ttest_on_dct / student_ttest_on_dct / mann_whitney）、tested_variable（固定 delta_ct）、dct、significance、outlier_check （真实算法引擎执行，非大模型生成）

act_qpcr_ddct input schema
{
  "type": "object",
  "required": [
    "ctrl_ct",
    "ctrl_ref_ct",
    "exp_ct",
    "exp_ref_ct"
  ],
  "properties": {
    "gene": {
      "type": "string",
      "description": "目的基因名，如 NLRP3 / TREM2"
    },
    "exp_ct": {
      "type": "string",
      "description": "处理组目的基因 Ct，逗号分隔，如 20.1,20.4,20.2"
    },
    "ctrl_ct": {
      "type": "string",
      "description": "对照组目的基因 Ct，逗号分隔，如 22.5,22.8,22.6"
    },
    "ref_gene": {
      "type": "string",
      "description": "内参基因名，默认 GAPDH"
    },
    "exp_ref_ct": {
      "type": "string",
      "description": "处理组内参基因 Ct，逗号分隔，与 exp_ct 一一对应，如 18.2,18.5,18.3"
    },
    "ctrl_ref_ct": {
      "type": "string",
      "description": "对照组内参基因 Ct，逗号分隔，与 ctrl_ct 一一对应，如 18.3,18.1,18.4"
    }
  }
}
act_qpcr_ddct annotations
{
  "title": "qPCR 相对表达量（2^-ΔΔCt）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_randomize
Advertised by the server during the last successful anonymous check.
Advertised read-only

【随机化分组】 用户要随机分组、随机数字表、区组随机、分层随机 返回：分组结果表 （真实算法引擎执行，非大模型生成）

act_randomize input schema
{
  "type": "object",
  "required": [
    "n_subjects",
    "groups"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "description": "随机种子（固定才可复现）"
    },
    "groups": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "分组名称数组，如 [\"干预组\",\"对照组\"]（必须是数组，不是数字）"
    },
    "method": {
      "type": "string",
      "description": "simple 简单 / block 区组 / stratified 分层 / minimization 最小化"
    },
    "block_size": {
      "type": "integer",
      "description": "区组长度（block 方法用）"
    },
    "n_subjects": {
      "type": "integer",
      "description": "总样本量，如 60"
    }
  }
}
act_randomize annotations
{
  "title": "随机化分组",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_risk_ratio
Advertised by the server during the last successful anonymous check.
Advertised read-only

【相对危险度 RR】 用户给的是四格表人数，要 RR 或 OR 及 CI 返回：RR、OR、95%CI （真实算法引擎执行，非大模型生成）

act_risk_ratio input schema
{
  "type": "object",
  "required": [
    "exposed_events",
    "exposed_total",
    "unexposed_events",
    "unexposed_total"
  ],
  "properties": {
    "exposed_total": {
      "type": "integer",
      "description": "暴露组总数"
    },
    "exposed_events": {
      "type": "integer",
      "description": "暴露组事件数"
    },
    "unexposed_total": {
      "type": "integer",
      "description": "非暴露组总数"
    },
    "unexposed_events": {
      "type": "integer",
      "description": "非暴露组事件数"
    }
  }
}
act_risk_ratio annotations
{
  "title": "相对危险度 RR",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_rnaseq_deg
Advertised by the server during the last successful anonymous check.
Advertised read-only

【RNA-seq 差异分析】 用户有 RNA-seq 表达矩阵要做差异基因 返回：差异基因清单 （真实算法引擎执行，非大模型生成）

act_rnaseq_deg input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "groups": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "分组"
    },
    "log2fc": {
      "type": "number",
      "description": "log2FC 阈值"
    },
    "data_json": {
      "type": "object",
      "description": "表达矩阵"
    },
    "fdr_threshold": {
      "type": "number",
      "description": "FDR"
    }
  }
}
act_rnaseq_deg annotations
{
  "title": "RNA-seq 差异分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_roc
Advertised by the server during the last successful anonymous check.
Advertised read-only

【ROC 曲线与 AUC】 用户有金标准标签和预测分数，要算 AUC、画 ROC 返回：AUC、最优阈值、敏感度特异度 （真实算法引擎执行，非大模型生成）

act_roc input schema
{
  "type": "object",
  "required": [
    "labels",
    "scores"
  ],
  "properties": {
    "labels": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "真实标签 0/1"
    },
    "scores": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "预测分数/概率"
    }
  }
}
act_roc annotations
{
  "title": "ROC 曲线与 AUC",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_sas_r_code
Advertised by the server during the last successful anonymous check.
Advertised read-only

【生成可复现 SAS/R 代码】 用户要把分析结果导出成 R / SAS / Python 代码复现 返回：推荐统计方法与代码 （真实算法引擎执行，非大模型生成）

act_sas_r_code input schema
{
  "type": "object",
  "required": [
    "design"
  ],
  "properties": {
    "design": {
      "type": "string",
      "description": "研究设计"
    },
    "n_groups": {
      "type": "integer",
      "description": "组数"
    },
    "outcome_type": {
      "type": "string",
      "description": "结局类型"
    }
  }
}
act_sas_r_code annotations
{
  "title": "生成可复现 SAS/R 代码",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_scrna_analyze
Advertised by the server during the last successful anonymous check.
Advertised read-only

【单细胞分析】 用户有单细胞数据要做聚类降维 返回：聚类结果与 UMAP （真实算法引擎执行，非大模型生成）

act_scrna_analyze input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "n_pcs": {
      "type": "integer",
      "description": "主成分数"
    },
    "data_json": {
      "type": "object",
      "description": "单细胞矩阵"
    },
    "min_genes": {
      "type": "integer",
      "description": "最少基因数"
    },
    "max_mito_pct": {
      "type": "number",
      "description": "线粒体比例上限"
    }
  }
}
act_scrna_analyze annotations
{
  "title": "单细胞分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_scrna_celltype
Advertised by the server during the last successful anonymous check.
Advertised read-only

【单细胞细胞类型注释】 用户要自动注释细胞类型 返回：细胞类型注释 （真实算法引擎执行，非大模型生成）

act_scrna_celltype input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "data_json": {
      "type": "object",
      "description": "必填。数据对象（不是字符串）。矩阵形式：{\"matrix\": [[行1各列数值...], [行2...]], \"rows\": [\"基因/特征名\"], \"cols\": [\"样本名\"]}；组学结果另可带 {\"groups\": [\"组A\",\"组A\",\"组B\"...]}（与 cols 一一对应）、{\"p_values\": [...], \"log2fc\": [...]}（若已有差异结果）。实测缺此字段会被拒：Field required: data_json"
    }
  }
}
act_scrna_celltype annotations
{
  "title": "单细胞细胞类型注释",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_scrna_markers
Advertised by the server during the last successful anonymous check.
Advertised read-only

【单细胞 Marker 基因】 用户要找各细胞群的 marker 基因 返回：各群 marker （真实算法引擎执行，非大模型生成）

act_scrna_markers input schema
{
  "type": "object",
  "required": [
    "data_json"
  ],
  "properties": {
    "data_json": {
      "type": "object",
      "description": "必填。数据对象（不是字符串）。矩阵形式：{\"matrix\": [[行1各列数值...], [行2...]], \"rows\": [\"基因/特征名\"], \"cols\": [\"样本名\"]}；组学结果另可带 {\"groups\": [\"组A\",\"组A\",\"组B\"...]}（与 cols 一一对应）、{\"p_values\": [...], \"log2fc\": [...]}（若已有差异结果）。实测缺此字段会被拒：Field required: data_json"
    }
  }
}
act_scrna_markers annotations
{
  "title": "单细胞 Marker 基因",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_sequence_enzyme
Advertised by the server during the last successful anonymous check.
Advertised read-only

【酶切位点分析】 用户问序列上有哪些酶切位点、能不能切开 返回：酶切位点清单 （真实算法引擎执行，非大模型生成）

act_sequence_enzyme input schema
{
  "type": "object",
  "required": [
    "sequence"
  ],
  "properties": {
    "sequence": {
      "type": "string",
      "description": "核酸序列"
    }
  }
}
act_sequence_enzyme annotations
{
  "title": "酶切位点分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_sequence_orf
Advertised by the server during the last successful anonymous check.
Advertised read-only

【ORF 预测】 用户要在序列里找开放阅读框 返回：ORF 列表与位置 （真实算法引擎执行，非大模型生成）

act_sequence_orf input schema
{
  "type": "object",
  "required": [
    "sequence"
  ],
  "properties": {
    "sequence": {
      "type": "string",
      "description": "核酸序列"
    }
  }
}
act_sequence_orf annotations
{
  "title": "ORF 预测",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_sequence_plasmid
Advertised by the server during the last successful anonymous check.
Advertised read-only

【质粒图谱】 用户要画质粒图谱、看载体结构 返回：质粒图谱 （真实算法引擎执行，非大模型生成）

act_sequence_plasmid input schema
{
  "type": "object",
  "required": [
    "sequence"
  ],
  "properties": {
    "sequence": {
      "type": "string",
      "description": "质粒序列"
    }
  }
}
act_sequence_plasmid annotations
{
  "title": "质粒图谱",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_sequence_translate
Advertised by the server during the last successful anonymous check.
Advertised read-only

【序列翻译】 用户贴了核酸序列要翻译成氨基酸 返回：氨基酸序列 （真实算法引擎执行，非大模型生成）

act_sequence_translate input schema
{
  "type": "object",
  "required": [
    "sequence"
  ],
  "properties": {
    "sequence": {
      "type": "string",
      "description": "核酸序列"
    }
  }
}
act_sequence_translate annotations
{
  "title": "序列翻译",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_smd_balance
Advertised by the server during the last successful anonymous check.
Advertised read-only

【SMD 均衡性检查】 用户做 PSM/IPTW 后要检查协变量均衡（标准化均数差） 返回：各协变量 SMD 与均衡判断 （真实算法引擎执行，非大模型生成）

act_smd_balance input schema
{
  "type": "object",
  "required": [
    "covariates",
    "treatment"
  ],
  "properties": {
    "treatment": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "分组 0/1"
    },
    "covariates": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "协变量矩阵：每行一个样本、每列一个变量"
    }
  }
}
act_smd_balance annotations
{
  "title": "SMD 均衡性检查",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_stat_center
Advertised by the server during the last successful anonymous check.
Advertised read-only

【统计中心（97 个统计工具统一入口）】 用户要跑的统计检验没被其他专门工具覆盖时用这个：比较差异、找关系、看生存、做诊断、队列预处理、综合证据六类共 97 个工具（Kappa、Bland-Altman、ICC、VIF、PCA、聚类、Friedman、McNemar、游程、符号检验、趋势卡方、Meta 各件等都从这里走） 返回：该统计工具的完整结果（含统计量、P 值、95%CI、解读） （真实算法引擎执行，非大模型生成）

act_stat_center input schema
{
  "type": "object",
  "required": [
    "tool_id"
  ],
  "properties": {
    "payload": {
      "type": "object",
      "description": "该工具需要的数据字段（不要把数据包成字符串）。常见字段：group1/group2（两组数值数组）、groups（{组名:[数值]}）、values、x/y、time/event、gold/score、es/se（效应量与标准误）、m1/m2、r1/r2、row_var/col_var、features/label"
    },
    "tool_id": {
      "type": "string",
      "description": "统计工具 id，必须是下列之一：比较差异[ttest,welch,mwu,wilcoxon,anova,welchAnova,kw,friedman,rmAnova,ancova,chi2,fisher,mcnemar,cochranQ,posthoc,multicorr,homogeneity,normality,brunner,signTest,runsTest,effectSize,pInverse]、找关系[pearson,spearman,kendall,linearReg,multiLinear,logistic,logisticModel,vif,regDiag,icc,blan"
    }
  }
}
act_stat_center annotations
{
  "title": "统计中心（97 个统计工具统一入口）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_survival_analyze
Advertised by the server during the last successful anonymous check.
Advertised read-only

【生存分析（KM/Cox 全流程）】 用户有随访时间与结局事件，要做生存分析、算 HR、出生存曲线 返回：生存曲线、中位生存、HR、log-rank P （真实算法引擎执行，非大模型生成）

act_survival_analyze input schema
{
  "type": "object",
  "required": [
    "data"
  ],
  "properties": {
    "data": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "逐行数据，每行含时间/事件/分组/协变量"
    },
    "time_col": {
      "type": "string",
      "description": "随访时间列名"
    },
    "event_col": {
      "type": "string",
      "description": "结局事件列名（1=事件）"
    },
    "group_col": {
      "type": "string",
      "description": "分组列名"
    },
    "analysis_type": {
      "type": "string",
      "description": "km 或 cox"
    },
    "covariate_cols": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Cox 协变量列名"
    }
  }
}
act_survival_analyze annotations
{
  "title": "生存分析（KM/Cox 全流程）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_table_one
Advertised by the server during the last successful anonymous check.
Advertised read-only

【生成 Table 1（基线特征表）】 用户有数据文件，要出论文第一张基线表 Table 1 返回：Table 1 表格 + 可选段落 （真实算法引擎执行，非大模型生成）

act_table_one input schema
{
  "type": "object",
  "required": [
    "file_id",
    "group_variable"
  ],
  "properties": {
    "file_id": {
      "type": "integer",
      "description": "数据文件 id（可不填，助手会自动用你最近上传的数据）"
    },
    "test_method": {
      "type": "string",
      "description": "auto/t/nonparametric/chi2"
    },
    "group_variable": {
      "type": "string",
      "description": "分组变量列名"
    },
    "generate_paragraph": {
      "type": "boolean",
      "description": "是否同时生成论文表述段落"
    },
    "variables_to_include": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "纳入的变量列名"
    }
  }
}
act_table_one annotations
{
  "title": "生成 Table 1（基线特征表）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_table_one_subgroup
Advertised by the server during the last successful anonymous check.
Advertised read-only

【分组 Table 1（亚组表）】 用户要按某个变量做分层的基线表 返回：亚组表 （真实算法引擎执行，非大模型生成）

act_table_one_subgroup input schema
{
  "type": "object",
  "required": [
    "file_id",
    "group_variable",
    "subgroup_variable"
  ],
  "properties": {
    "file_id": {
      "type": "integer",
      "description": "数据文件 id"
    },
    "group_variable": {
      "type": "string",
      "description": "分组变量"
    },
    "subgroup_variable": {
      "type": "string",
      "description": "分层变量"
    },
    "variables_to_include": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "纳入变量"
    }
  }
}
act_table_one_subgroup annotations
{
  "title": "分组 Table 1（亚组表）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_tme_analyze
Advertised by the server during the last successful anonymous check.
Advertised read-only

【肿瘤微环境分析】 用户有 TILs/CD8/PD-L1 数据要评估肿瘤微环境 返回：微环境分型与预后提示 （真实算法引擎执行，非大模型生成）

act_tme_analyze input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "tils_pct": {
      "type": "number",
      "description": "TILs 占比"
    },
    "cd8_count": {
      "type": "number",
      "description": "CD8+ 细胞数"
    },
    "pd_l1_pos": {
      "type": "number",
      "description": "PD-L1 阳性率"
    },
    "cancer_type": {
      "type": "string",
      "description": "癌种"
    }
  }
}
act_tme_analyze annotations
{
  "title": "肿瘤微环境分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_tox_eval
Advertised by the server during the last successful anonymous check.
Advertised read-only

【毒理评估】 用户要评估候选物的毒性风险（hERG/DILI/遗传毒） 返回：毒性风险分级 （真实算法引擎执行，非大模型生成）

act_tox_eval input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "logP": {
      "type": "number",
      "description": "logP"
    },
    "hERG_IC50_nM": {
      "type": "number",
      "description": "hERG IC50 (nM)"
    },
    "daily_dose_mg": {
      "type": "number",
      "description": "日剂量 (mg)"
    },
    "expected_Cmax_nM": {
      "type": "number",
      "description": "预期 Cmax (nM)"
    }
  }
}
act_tox_eval annotations
{
  "title": "毒理评估",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_tox_predict
Advertised by the server during the last successful anonymous check.
Advertised read-only

【毒性预测（hERG/DILI）】 用户要评估化合物心脏/肝毒性风险 返回：毒性风险分级 （真实算法引擎执行，非大模型生成）

act_tox_predict input schema
{
  "type": "object",
  "required": [
    "smiles"
  ],
  "properties": {
    "smiles": {
      "type": "string",
      "description": "化合物 SMILES"
    },
    "endpoints": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "终点：hERG/DILI/Ames"
    }
  }
}
act_tox_predict annotations
{
  "title": "毒性预测（hERG/DILI）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_tukey_hsd
Advertised by the server during the last successful anonymous check.
Advertised read-only

【多组两两比较（Tukey HSD）】 用户做了 ANOVA 后要多组两两比较 返回：两两比较 P 值 （真实算法引擎执行，非大模型生成）

act_tukey_hsd input schema
{
  "type": "object",
  "required": [
    "groups"
  ],
  "properties": {
    "groups": {
      "type": "object",
      "description": "{组名: [数值...]}"
    }
  }
}
act_tukey_hsd annotations
{
  "title": "多组两两比较（Tukey HSD）",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
act_two_way_anova
Advertised by the server during the last successful anonymous check.
Advertised read-only

【双因素方差分析】 用户有两个因素要看主效应与交互作用 返回：主效应与交互 （真实算法引擎执行，非大模型生成）

act_two_way_anova input schema
{
  "type": "object",
  "required": [
    "group_a",
    "group_b"
  ],
  "properties": {
    "values": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "观测值"
    },
    "group_a": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "因素 A 水平"
    },
    "group_b": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "因素 B 水平"
    }
  }
}
act_two_way_anova annotations
{
  "title": "双因素方差分析",
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
sanyu_list_actions
Advertised by the server during the last successful anonymous check.
Advertised read-only

列出三域医研全部真算法动作的摘要（id / 名称 / 适用场景 / 产出 / 必填参数 / 计费）。仅在不确定该用哪个动作时调用；已知动作 id 可直接调用同名工具。

sanyu_list_actions input schema
{
  "type": "object",
  "required": [],
  "properties": {}
}
sanyu_list_actions annotations
{
  "title": "动作目录",
  "readOnlyHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
2322 ms
95th percentile latency
2322 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 2322 ms · metadata changed · 106 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http sanyu-research-engine-mcp https://sanyu.wentangkeji.com/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add sanyu-research-engine-mcp --url https://sanyu.wentangkeji.com/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable sanyu-research-engine-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "sanyu-research-engine-mcp": {
      "url": "https://sanyu.wentangkeji.com/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "sanyu-research-engine-mcp": {
      "type": "streamableHttp",
      "url": "https://sanyu.wentangkeji.com/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start sanyu-research-engine-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "sanyu-research-engine-mcp": {
      "type": "http",
      "url": "https://sanyu.wentangkeji.com/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http sanyu-research-engine-mcp https://sanyu.wentangkeji.com/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://sanyu.wentangkeji.com/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "sanyu-research-engine-mcp": {
      "serverUrl": "https://sanyu.wentangkeji.com/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like SanYu Research Engine MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,557