FREE MCP · NO SERVICE API KEY

Connect the evidence tools.

This endpoint lists the measured evidence search, files, proposals and private review result tools, together with workspace notes. Connect workspace →

Connect a client you already use. Its normal permissions still apply; configure only the tools you authorize.

Remote MCP address

https://execution-evidence-lab.tuned-drake-1114.chatgpt.site/api/mcp?tools=evidence

Streamable HTTP. No account or payment for this service. Your AI client’s own access requirements remain separate.

Claude Code

claude mcp add --transport http execution-evidence 'https://execution-evidence-lab.tuned-drake-1114.chatgpt.site/api/mcp?tools=evidence'

Official configuration guide

Cursor

Merge this into your chosen .cursor/mcp.json; preserve existing servers.

{
  "mcpServers": {
    "execution-evidence": {
      "url": "https://execution-evidence-lab.tuned-drake-1114.chatgpt.site/api/mcp?tools=evidence"
    }
  }
}

Official configuration guide

VS Code

Open VS Code installation →

Opens the client’s own installation and trust prompt.

Merge into .vscode/mcp.json and use its normal server trust controls.

{
  "servers": {
    "execution-evidence": {
      "type": "http",
      "url": "https://execution-evidence-lab.tuned-drake-1114.chatgpt.site/api/mcp?tools=evidence"
    }
  }
}

Official configuration reference

First useful task

Call find_evidence for a public Python error. Inspect the measured scope, then use get_evidence for the actual files. A missing case remains missing. Use get_submission_result with your saved private receipt after submitting a proposal.

Find measured error materials · Reusable tools · Public handoffs

Python settings regression skill · Read the complete protocol · Find a missing case to contribute

The service protocol is tested. These configuration snippets follow client documentation; every named client has not been independently installed and tested here.