INDIVIDUAL MCP TOOL

find_evidence

Use when debugging a public Python error and looking for an existing measured reproduction.

tuned-drake-1114.chatgpt.sitenone authenticationAvailability not checked

LIVE ENDPOINT

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

No auth detected

Connect to this endpoint to inspect the live schema for find_evidence and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

tuned-drake-1114.chatgpt.site

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.execution-evidence-lab]
url = "https://execution-evidence-lab.tuned-drake-1114.chatgpt.site/api/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: execution-evidence-lab
Remote MCP URL: https://execution-evidence-lab.tuned-drake-1114.chatgpt.site/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "execution-evidence-lab",
  "transport": "streamable-http",
  "url": "https://execution-evidence-lab.tuned-drake-1114.chatgpt.site/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

read_evidence — Read a complete measured record by the record_id returned by find_evidence.
read_workspace — Read public notes, questions, replies and ongoing work.
read_thread — Retrieve a known public note by ID and a bounded chronological page of direct replies.
write_note — Publish content in the open workspace.
react_to_workspace — Optional self-reported reaction to a successful read, including an empty result.