VerifiMind PEAS MCP

An open-source MCP server that runs concepts through three specialized LLM judges (Innovation, Ethics, Security) for structured multi-LLM critique. It supports multi-vendor integration including Gemini, Claude, GPT, Groq, Cerebras, Mistral, and Ollama, providing auditable reasoning and validation-first methodology for ethical and secure application development.

Visit creator35lwb-web

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.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by creator35lwb-web

You need:Connect using an MCP client such as Claude Desktop, Claude Code, or Cursor

MCP endpoint (Streamable HTTP)

https://verifimind.ysenseai.org/mcp/

Vendor documentation

What its tools do

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

13 of 13 have a description · 0 of 13 declare behavior hints · 0 of 13 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 3:46 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Evaluate innovation and competitive positioning of a concept
Check ethics, compliance, and jurisdictional risks
Perform security validation against OWASP standards
Run full Trinity critique with multiple LLM agents

Source and maintenance

Community listingRegistry 3.45.0

mcp-registry: io.github.creator35lwb-web/verifimind-genesis@3.45.0 Source repository

Maintenance checked: Nov 6, 2026, 3:14 PM UTC

Protocol and capabilities

Server: verifimind-genesis 0.5.68
MCP protocol negotiated in check: 2025-11-25
Tools: 13 advertised
Resources: 4 advertised
Resource templates: 0 advertised
Prompts: 0 advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  },
  "logging": {},
  "prompts": {
    "listChanged": true
  },
  "resources": {
    "subscribe": false,
    "listChanged": true
  }
}

Tools

13 advertised

consult_agent_x — Consult Agent X

Advertised by the server during the last successful anonymous check.

Consult X Intelligent agent for innovation and strategy analysis. X Intelligent specializes in: - Innovation potential assessment - Strategic value analysis - Market opportunity identification - Competitive positioning - Growth potential evaluation BYOK (v0.4.5): Pass llm_provider and api_key to use your own LLM. If only api_key is provided, the provider is auto-detected from the key prefix. Keys are ephemeral (never stored) and garbage collected after the call.

consult_agent_x input schema

{
  "type": "object",
  "required": [
    "concept_name",
    "concept_description"
  ],
  "properties": {
    "detail": {
      "type": "string",
      "default": "standard"
    },
    "api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional API key for the provider (ephemeral, never stored)"
    },
    "context": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional additional context or background"
    },
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "concept_name": {
      "type": "string",
      "description": "Short name or title of the concept"
    },
    "llm_provider": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')"
    },
    "concept_description": {
      "type": "string",
      "description": "Detailed description of the concept"
    }
  },
  "additionalProperties": false
}

consult_agent_x output schema

{
  "type": "object",
  "additionalProperties": true
}

consult_agent_z — Consult Agent Z

Advertised by the server during the last successful anonymous check.

Consult Z Guardian agent for ethical review and Z-Protocol enforcement. Z Guardian specializes in: - Ethical implications assessment - Privacy and data protection review - Bias and fairness analysis - Social impact evaluation - Z-Protocol compliance verification Z Guardian has VETO POWER. If veto_triggered is True, the concept should not proceed as it crosses ethical red lines. BYOK (v0.4.5): Pass llm_provider and api_key to use your own LLM. If only api_key is provided, the provider is auto-detected from the key prefix. Keys are ephemeral (never stored) and garbage collected after the call.

consult_agent_z input schema

{
  "type": "object",
  "required": [
    "concept_name",
    "concept_description"
  ],
  "properties": {
    "detail": {
      "type": "string",
      "default": "standard"
    },
    "api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional API key for the provider (ephemeral, never stored)"
    },
    "context": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional additional context or background"
    },
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "concept_name": {
      "type": "string",
      "description": "Short name or title of the concept"
    },
    "llm_provider": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')"
    },
    "prior_reasoning": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional reasoning from X agent to consider"
    },
    "concept_description": {
      "type": "string",
      "description": "Detailed description of the concept"
    }
  },
  "additionalProperties": false
}

consult_agent_z output schema

{
  "type": "object",
  "additionalProperties": true
}

consult_agent_cs — Consult Agent Cs

Advertised by the server during the last successful anonymous check.

Consult CS Security agent for security validation and Socratic interrogation. CS Security specializes in: - Security vulnerability assessment - Attack vector identification - Data security review - System integrity analysis - Socratic questioning (challenging assumptions) BYOK (v0.4.5): Pass llm_provider and api_key to use your own LLM. If only api_key is provided, the provider is auto-detected from the key prefix. Keys are ephemeral (never stored) and garbage collected after the call.

consult_agent_cs input schema

{
  "type": "object",
  "required": [
    "concept_name",
    "concept_description"
  ],
  "properties": {
    "detail": {
      "type": "string",
      "default": "standard"
    },
    "api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional API key for the provider (ephemeral, never stored)"
    },
    "context": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional additional context or background"
    },
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "concept_name": {
      "type": "string",
      "description": "Short name or title of the concept"
    },
    "llm_provider": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional LLM provider override ('groq', 'anthropic', 'openai', 'gemini', 'mistral', 'ollama', 'mock')"
    },
    "prior_reasoning": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional reasoning from X and Z agents to consider"
    },
    "concept_description": {
      "type": "string",
      "description": "Detailed description of the concept"
    }
  },
  "additionalProperties": false
}

consult_agent_cs output schema

{
  "type": "object",
  "additionalProperties": true
}

run_full_trinity — Run Full Trinity

Advertised by the server during the last successful anonymous check.

Run complete X → Z → CS Trinity validation with Chain of Thought. This tool orchestrates all three agents in sequence: 1. X Intelligent analyzes innovation and strategy 2. Z Guardian reviews ethics (sees X's reasoning) 3. CS Security validates security (sees X and Z reasoning) 4. Results are synthesized into a unified assessment Each agent sees the reasoning of previous agents, enabling true collaborative analysis with full transparency. BYOK (v0.4.5): Pass llm_provider/api_key for all agents, or use per-agent overrides (x_provider/x_api_key, z_provider/z_api_key, cs_provider/cs_api_key). Per-agent params take priority over global. Keys are ephemeral (never stored) and garbage collected after the call.

run_full_trinity input schema

{
  "type": "object",
  "required": [
    "concept_name",
    "concept_description"
  ],
  "properties": {
    "detail": {
      "type": "string",
      "default": "standard",
      "description": "Reasoning verbosity (v0.5.44) — \"standard\" (default) returns the\nauditable `reasoning` block (per-step reasoning, ethics scoring breakdown\n+ framework citations, Socratic questions, threat assessment) alongside\nthe scores; \"full\" adds per-step evidence and the heaviest structured\nfields (12-dimension matrix, 6-stage record, MACP assessment); \"summary\"\nomits the reasoning block for the smallest payload. The block is additive —\nexisting response fields are unchanged at every level."
    },
    "api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional global API key for all agents (ephemeral, never stored)"
    },
    "context": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional additional context or background"
    },
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "x_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional API key override for X agent only"
    },
    "z_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional API key override for Z agent only"
    },
    "cs_api_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional API key override for CS agent only"
    },
    "x_provider": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional provider override for X agent only"
    },
    "z_provider": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional provider override for Z agent only"
    },
    "cs_provider": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional provider override for CS agent only"
    },
    "concept_name": {
      "type": "string",
      "description": "Short name or title of the concept"
    },
    "llm_provider": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional global LLM provider for all agents"
    },
    "save_to_history": {
      "type": "boolean",
      "default": false,
      "description": "Whether to save the full result to validation history\n(default: False). The store is shared and instance-local, retains at\nmost the 20 newest opt-in results, evicts oldest entries on every\nread/write, and clears when the instance is replaced. It has no fixed\ntime-retention guarantee. Leave False for private or sensitive concepts.\nDuring security maintenance a separately supplied user_uuid has no\neffect: no UUID-keyed validation history is written for it."
    },
    "concept_description": {
      "type": "string",
      "description": "Detailed description of the concept"
    }
  },
  "additionalProperties": false
}

run_full_trinity output schema

{
  "type": "object",
  "additionalProperties": true
}

list_prompt_templates — List Prompt Templates

Advertised by the server during the last successful anonymous check.

List available prompt templates with optional filtering. v0.4.0 Unified Prompt Templates feature.

list_prompt_templates input schema

{
  "type": "object",
  "properties": {
    "tags": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Comma-separated tags to filter by (e.g., 'genesis:phase-1,default')"
    },
    "agent_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter by agent (X, Z, CS, or 'all')"
    },
    "category": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Filter by category (startup, security, ethics, etc.)"
    },
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}

list_prompt_templates output schema

{
  "type": "object",
  "additionalProperties": true
}

get_prompt_template — Get Prompt Template

Advertised by the server during the last successful anonymous check.

Get a specific prompt template by ID. v0.4.0 Unified Prompt Templates feature.

get_prompt_template input schema

{
  "type": "object",
  "required": [
    "template_id"
  ],
  "properties": {
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "template_id": {
      "type": "string",
      "description": "Unique template identifier"
    },
    "include_content": {
      "type": "boolean",
      "default": true,
      "description": "Whether to include full template content"
    }
  },
  "additionalProperties": false
}

get_prompt_template output schema

{
  "type": "object",
  "additionalProperties": true
}

export_prompt_template — Export Prompt Template

Advertised by the server during the last successful anonymous check.

Export a prompt template to Markdown or JSON format. v0.4.0 Unified Prompt Templates feature.

export_prompt_template input schema

{
  "type": "object",
  "required": [
    "template_id"
  ],
  "properties": {
    "format": {
      "type": "string",
      "default": "markdown",
      "description": "Export format ('markdown' or 'json')"
    },
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "template_id": {
      "type": "string",
      "description": "Template to export"
    }
  },
  "additionalProperties": false
}

export_prompt_template output schema

{
  "type": "object",
  "additionalProperties": true
}

register_custom_template — Register Custom Template

Advertised by the server during the last successful anonymous check.

register_custom_template input schema

{
  "type": "object",
  "required": [
    "name",
    "agent_id",
    "content"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Template display name"
    },
    "tags": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Comma-separated tags"
    },
    "content": {
      "type": "string",
      "description": "Template content with {variable} placeholders"
    },
    "agent_id": {
      "type": "string",
      "description": "Target agent (X, Z, CS, or 'all')"
    },
    "category": {
      "type": "string",
      "default": "custom",
      "description": "Template category (default: 'custom')"
    },
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Template description"
    }
  },
  "additionalProperties": false
}

register_custom_template output schema

{
  "type": "object",
  "additionalProperties": true
}

import_template_from_url — Import Template From Url

Advertised by the server during the last successful anonymous check.

Import a prompt template from a URL (GitHub Gist, raw file, etc.). v0.4.0 Unified Prompt Templates feature. Supports: - GitHub Gist URLs - Raw GitHub file URLs - Any HTTPS URL pointing to JSON/YAML template

import_template_from_url input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "URL to import template from"
    },
    "validate": {
      "type": "boolean",
      "default": true,
      "description": "Whether to validate template content (default: True)"
    },
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}

import_template_from_url output schema

{
  "type": "object",
  "additionalProperties": true
}

get_template_statistics — Get Template Statistics

Advertised by the server during the last successful anonymous check.

Get statistics about the template registry. v0.4.0 Unified Prompt Templates feature.

get_template_statistics input schema

{
  "type": "object",
  "properties": {
    "user_uuid": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}

get_template_statistics output schema

{
  "type": "object",
  "additionalProperties": true
}

coordination_handoff_create — Coordination Handoff Create

Advertised by the server during the last successful anonymous check.

Create a structured MACP v2.5 handoff record. TEMPORARILY DISABLED — this tool is contained pending a security repair (incident VM-IR-2026-07-28-COORD-01) and always returns a denial. Handoff bodies written through this tool were stored in a shared namespace that any unauthenticated caller could read. Nothing is stored or returned while containment is in force. Coordination state belongs in your own repository until private, owner-scoped storage ships. All arguments are accepted for schema stability and are ignored; no supplied value is stored, logged, or echoed back.

coordination_handoff_create input schema

{
  "type": "object",
  "required": [
    "agent_id",
    "session_type",
    "completed",
    "decisions",
    "artifacts",
    "pending",
    "blockers"
  ],
  "properties": {
    "pending": {
      "type": "array",
      "items": {}
    },
    "agent_id": {
      "type": "string"
    },
    "blockers": {
      "type": "array",
      "items": {}
    },
    "artifacts": {
      "type": "array",
      "items": {}
    },
    "completed": {
      "type": "array",
      "items": {}
    },
    "decisions": {
      "type": "array",
      "items": {}
    },
    "next_agent": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "pioneer_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "session_type": {
      "type": "string"
    }
  },
  "additionalProperties": false
}

coordination_handoff_create output schema

{
  "type": "object",
  "additionalProperties": true
}

coordination_handoff_read — Coordination Handoff Read

Advertised by the server during the last successful anonymous check.

Read the most recent coordination handoff record(s). TEMPORARILY DISABLED — this tool is contained pending a security repair (incident VM-IR-2026-07-28-COORD-01) and always returns a denial. This read path returned complete handoff bodies from a caller-selected namespace with no authenticated ownership check. It is closed to every caller — with or without a key — while owner-scoped access control is rebuilt. No record body is returned. All arguments are accepted for schema stability and are ignored.

coordination_handoff_read input schema

{
  "type": "object",
  "properties": {
    "count": {
      "type": "integer",
      "default": 1
    },
    "agent_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "pioneer_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}

coordination_handoff_read output schema

{
  "type": "object",
  "additionalProperties": true
}

coordination_team_status — Coordination Team Status

Advertised by the server during the last successful anonymous check.

Return current team coordination state and session summary. TEMPORARILY DISABLED — this tool is contained pending a security repair (incident VM-IR-2026-07-28-COORD-01) and always returns a denial. This summary exposed agent identities, pending actions, open blockers, and a timestamped activity index from a caller-selected namespace with no authenticated ownership check — enough to enumerate a namespace before reading it. It is closed to every caller while owner-scoped access control is rebuilt. All arguments are accepted for schema stability and are ignored.

coordination_team_status input schema

{
  "type": "object",
  "properties": {
    "pioneer_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}

coordination_team_status output schema

{
  "type": "object",
  "additionalProperties": true
}

Prompts

0 advertised

No prompt definitions available.

Resources

4 advertised

get_master_prompt

Advertised by the server during the last successful anonymous check.

Genesis Methodology — Live Production Prompts Returns the X / Z / CS prompt contract generated directly from the agents' in-code configuration, so it always matches what the agents actually run (v0.5.43). Includes roles, focus areas, inference settings, and the verbatim production prompt templates. URI: genesis://config/master_prompt Format: Markdown

get_master_prompt URI

genesis://config/master_prompt

MIME type: text/plain

get_latest_validation_resource

Advertised by the server during the last successful anonymous check.

Latest Validation — Privacy-Safe Summary Returns a NON-IDENTIFYING summary of the most recent validation (verdict, scores, timestamp). Concept names and descriptions are NOT exposed: the validation-history store is shared across all clients of this server instance, so returning raw concept text would leak one caller's idea to another (v0.5.43 cross-tenant privacy fix). URI: genesis://history/latest Format: JSON

get_latest_validation_resource URI

genesis://history/latest

MIME type: text/plain

get_all_validations

Advertised by the server during the last successful anonymous check.

Validation History — Aggregate Statistics Only Returns aggregate statistics over the shared validation history (total retained count, score/verdict distribution, last-updated, and the enforced retention contract — never the per-concept names or descriptions. The history store is instance-global; exposing raw entries here would leak other clients' concepts (v0.5.43 privacy fix). URI: genesis://history/all Format: JSON

get_all_validations URI

genesis://history/all

MIME type: text/plain

get_project_info_resource

Advertised by the server during the last successful anonymous check.

Project Information Returns metadata about the VerifiMind-PEAS project including architecture, agent roles, version information, and documentation links. URI: genesis://state/project_info Format: JSON

get_project_info_resource URI

genesis://state/project_info

MIME type: text/plain

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 (1 of 1 answered).

2026-11-06: 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: 887 ms
95th percentile latency: 887 ms

Maintenance history

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

Nov 6, 2026, 3:46 PM UTC · probe · passed · 887 ms · metadata changed · 13 tool(s), 4 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 verifimind-peas-mcp https://verifimind.ysenseai.org/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 verifimind-peas-mcp --url https://verifimind.ysenseai.org/mcp/

Cursor

Merge this server into .cursor/mcp.json in your project, then enable verifimind-peas-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "verifimind-peas-mcp": {
      "url": "https://verifimind.ysenseai.org/mcp/"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "verifimind-peas-mcp": {
      "type": "streamableHttp",
      "url": "https://verifimind.ysenseai.org/mcp/",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start verifimind-peas-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "verifimind-peas-mcp": {
      "type": "http",
      "url": "https://verifimind.ysenseai.org/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 verifimind-peas-mcp https://verifimind.ysenseai.org/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://verifimind.ysenseai.org/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": {
    "verifimind-peas-mcp": {
      "serverUrl": "https://verifimind.ysenseai.org/mcp/"
    }
  }
}

Let your agent find its tools

Find servers like VerifiMind PEAS 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 4,727

VerifiMind PEAS MCP

Endpoint and access

What its tools do

Not annotated (13)

Checks and signals

What you can do with it

Source and maintenance

Protocol and capabilities

Tools

Prompts

Resources

90-day uptime

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other ai and machine learning servers