Koskamo

SavantCat Compliance MCP

提供中国AI合规与备案的条文级问答服务,覆盖生成式AI备案、AI生成内容标识、深度合成及算法备案等5部法规的42个具体条款。支持按条号检索法规原文(含SHA256指纹)、场景自查及应办清单,旨在帮助中小企业进行合规性自查与落地。

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.

SavantCat Compliance MCP logo, by 合尘猫 SavantCatVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by 合尘猫 SavantCat
MCP endpoint (Streamable HTTP)
https://savantcat.cn/mcp-compliance
Vendor documentation

What its tools do

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

8 of 8 have a description · 8 of 8 declare behavior hints · 0 of 7 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to savantcat.cn ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • 查询生成式AI服务备案的具体流程与要求
  • 获取AI生成内容显式与隐式标识的技术规范
  • 自查算法推荐服务是否具备舆论属性需备案
  • 检索深度合成服务提供者的实名认证与评估义务

Source and maintenance

Vendor evidenceRegistry 1.1.1
Maintenance checked

Protocol and capabilities

Server
savantcat-ai-compliance 1.1.1
MCP protocol negotiated in check
2025-11-25
Tools
8 advertised
Resources
0 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

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

合尘猫 · 中国 AI 合规与备案知识库。收录《生成式人工智能服务管理暂行办法》《人工智能生成合成内容标识办法》《互联网信息服务深度合成管理规定》《互联网信息服务算法推荐管理规定》的逐条要求,回答「要不要备案」「要不要标注 AI 生成」「AI 客服上线前要做什么」「用第三方大模型 API 义务在谁身上」这类问题。所有结论均标注法规条文依据,并用 filing_route 给出应办事项清单。

Tools

8 advertised

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

列出全部合规条目的标题清单。 Args: cluster: 可选,按集群过滤。可选值 genai-interim(生成式AI暂行办法) / ai-content-label(AI生成合成内容标识) / deep-synthesis(深度合成) / algo-recommendation(算法推荐与备案) / filing-practice(备案实操)

list_topics input schema
{
  "type": "object",
  "title": "list_topicsArguments",
  "properties": {
    "cluster": {
      "type": "string",
      "title": "Cluster",
      "default": ""
    }
  }
}
list_topics output schema
{
  "type": "object",
  "title": "list_topicsOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
list_topics annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
search_compliance
Advertised by the server during the last successful anonymous check.
Advertised read-only

按关键词检索中国 AI 合规条目,返回最相关的若干条(含结论与条文依据)。 Args: query: 检索词,如「AI 客服 备案」「AI 生成内容 标注」「训练数据 合法来源」「大数据杀熟」 top_k: 返回条数,默认 5

search_compliance input schema
{
  "type": "object",
  "title": "search_complianceArguments",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "title": "Query"
    },
    "top_k": {
      "type": "integer",
      "title": "Top K",
      "default": 5
    }
  }
}
search_compliance output schema
{
  "type": "object",
  "title": "search_complianceOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
search_compliance annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_requirement
Advertised by the server during the last successful anonymous check.
Advertised read-only

按 slug 取一条合规要求的完整内容(正文 + 依据条文 + 落地动作 + 常见追问)。 Args: slug: 条目标识,先用 list_topics 或 search_compliance 取得

get_requirement input schema
{
  "type": "object",
  "title": "get_requirementArguments",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "title": "Slug"
    }
  }
}
get_requirement output schema
{
  "type": "object",
  "title": "get_requirementOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
get_requirement annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
self_check
Advertised by the server during the last successful anonymous check.
Advertised read-only

按场景出合规自查清单:把命中条目的「落地动作」汇总成可勾选待办,并列出条文依据。 Args: scope: 场景或关键词,如「AI 客服」「营销文案 标注」「小程序 上架」「全量」; 留空则返回全量自查清单

self_check input schema
{
  "type": "object",
  "title": "self_checkArguments",
  "properties": {
    "scope": {
      "type": "string",
      "title": "Scope",
      "default": ""
    }
  }
}
self_check output schema
{
  "type": "object",
  "title": "self_checkOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
self_check annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
filing_route
Advertised by the server during the last successful anonymous check.
Advertised read-only

判断一项 AI 服务要办哪些手续(备案/安全评估/标识),逐条给出法规依据。 Args: public_facing: 是否面向中国境内公众提供服务(仅内部使用请传 false) generates_content: 是否能生成文本/图片/音频/视频等内容 edits_face_or_voice: 是否提供人脸、人声等生物识别信息编辑功能(换脸、AI 配音、数字人) only_internal_use: 是否仅企业内部使用、不对外提供

filing_route input schema
{
  "type": "object",
  "title": "filing_routeArguments",
  "properties": {
    "public_facing": {
      "type": "boolean",
      "title": "Public Facing",
      "default": true
    },
    "generates_content": {
      "type": "boolean",
      "title": "Generates Content",
      "default": true
    },
    "only_internal_use": {
      "type": "boolean",
      "title": "Only Internal Use",
      "default": false
    },
    "edits_face_or_voice": {
      "type": "boolean",
      "title": "Edits Face Or Voice",
      "default": false
    }
  }
}
filing_route output schema
{
  "type": "object",
  "title": "filing_routeOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
filing_route annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
regulation_info
Advertised by the server during the last successful anonymous check.
Advertised read-only

获取收录法规清单(名称、发布/施行日期、条数、官方原文链接、核心要求)。

regulation_info input schema
{
  "type": "object",
  "title": "regulation_infoArguments",
  "properties": {}
}
regulation_info output schema
{
  "type": "object",
  "title": "regulation_infoOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
regulation_info annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_article
Advertised by the server during the last successful anonymous check.
Advertised read-only

按条号取某部法规的条文**逐字原文**,并附内容指纹与官方原文链接。 与 get_requirement 的分工:get_requirement 按「问题」取整条合规要求(含结论与落地动作); get_article 按「条号」取条文原文,用于逐字核对、引用与溯源。 Args: law: 法规名或集群标识。可写全称(《生成式人工智能服务管理暂行办法》)、 简称(标识办法 / 算法推荐规定)或 cluster (genai-interim / ai-content-label / deep-synthesis / algo-recommendation) article: 条号,支持「第十条」「10」「第10条」三种写法

get_article input schema
{
  "type": "object",
  "title": "get_articleArguments",
  "required": [
    "law",
    "article"
  ],
  "properties": {
    "law": {
      "type": "string",
      "title": "Law"
    },
    "article": {
      "type": "string",
      "title": "Article"
    }
  }
}
get_article output schema
{
  "type": "object",
  "title": "get_articleOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
get_article annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
search_articles
Advertised by the server during the last successful anonymous check.
Advertised read-only

在**某一部法规内部**按关键词检索条文,返回命中条号 + 条文摘录。 用途:已经知道是哪部法规,要定位「哪一条讲了这件事」。 Args: law: 法规名或集群标识(同 get_article 的 law 参数) keywords: 检索词,如「训练数据 合法来源」「标识 元数据」「备案 十日」 top_k: 返回条数,默认 5

search_articles input schema
{
  "type": "object",
  "title": "search_articlesArguments",
  "required": [
    "law",
    "keywords"
  ],
  "properties": {
    "law": {
      "type": "string",
      "title": "Law"
    },
    "top_k": {
      "type": "integer",
      "title": "Top K",
      "default": 5
    },
    "keywords": {
      "type": "string",
      "title": "Keywords"
    }
  }
}
search_articles output schema
{
  "type": "object",
  "title": "search_articlesOutput",
  "required": [
    "result"
  ],
  "properties": {
    "result": {
      "type": "string",
      "title": "Result"
    }
  }
}
search_articles annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

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
5391 ms
95th percentile latency
5391 ms

Maintenance history

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

  • · probe · passed · 5391 ms · metadata changed · 8 tool(s), 0 resource(s), 0 resource template(s), 0 prompt(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 savantcat-compliance-mcp https://savantcat.cn/mcp-compliance

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 savantcat-compliance-mcp --url https://savantcat.cn/mcp-compliance

Cursor

Merge this server into .cursor/mcp.json in your project, then enable savantcat-compliance-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "savantcat-compliance-mcp": {
      "url": "https://savantcat.cn/mcp-compliance"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "savantcat-compliance-mcp": {
      "type": "streamableHttp",
      "url": "https://savantcat.cn/mcp-compliance",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start savantcat-compliance-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "savantcat-compliance-mcp": {
      "type": "http",
      "url": "https://savantcat.cn/mcp-compliance"
    }
  }
}

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 savantcat-compliance-mcp https://savantcat.cn/mcp-compliance

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://savantcat.cn/mcp-compliance

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "savantcat-compliance-mcp": {
      "serverUrl": "https://savantcat.cn/mcp-compliance"
    }
  }
}

Let your agent find its tools

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

Do you run SavantCat Compliance MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing