Agent Cockpit MCP Server

by chutingyean Your server? Claim it

local only

Agent Cockpit runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 6 Nov 2026.

Evidence-chain whiteboard for AI research agents: every claim traces back to its run and code.

—

Installs / week

npm · @tingyen/agent-cockpit

402

Stars

0 open issues

6 Nov 2026

Last commit

from GitHub

AGPL-3.0

License

JavaScript

Nothing serious here today

Today is the operative word: we check Agent Cockpit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-cockpit -- npx -y @tingyen/agent-cockpit

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-cockpit": {
      "command": "npx",
      "args": [
        "-y",
        "@tingyen/agent-cockpit"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.agent-cockpit]
command = "npx"
args = ["-y", "@tingyen/agent-cockpit"]

.cursor/mcp.json

{
  "mcpServers": {
    "agent-cockpit": {
      "command": "npx",
      "args": [
        "-y",
        "@tingyen/agent-cockpit"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agent-cockpit": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@tingyen/agent-cockpit"
      ]
    }
  }
}

Alternatives to Agent Cockpit

same job, measured the same way

Paper Lantern

by paperlantern

Research intelligence for AI coding agents. 2M+ CS papers with evidence and tradeoffs.

answering

Jev Filter

by apixly-ai

Read-only semantic filtering, code search, log triage and traceable evidence for AI agents.

65 installs/wk local only

Noisy Coding

by noisy

Voice interface for Claude Code: talk to your agent and it talks back while it works.

local only

chargehand

by egoushka

Runs coding-agent workers on a codebase question; every claim in the answer carries evidence.

local only

Contextful

by inferensys

Efficient context management: code search, evidence packs, and memory for coding agents.

49 installs/wk local only

Knowl

by dat999zx

Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.

133 installs/wk answering

Coador

by automaticqa

Evidence-backed Android repository knowledge for humans and AI agents

59 installs/wk local only

LatticeRun

by latticerun

Let your AI agents claim a task, work inside it and report back on your LatticeRun task tree.

answering

Agent Cockpit — questions

Answers built from our own checks of this server.

Why is there no uptime for Agent Cockpit?

Agent Cockpit runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @tingyen/agent-cockpit.

How do I connect Agent Cockpit?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @tingyen/agent-cockpit straight from npm; nothing to host, nothing to sign up for.

Is Agent Cockpit open source?

Yes — it is published under the AGPL-3.0 licence, written in JavaScript and 402 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.