# Agent Cockpit (MCP server)

> Agent Cockpit is an MCP server that adds developer tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Evidence-chain whiteboard for AI research agents: every claim traces back to its run and code. It has 501 GitHub stars, is released under the AGPL-3.0 license and runs locally with npx -y @tingyen/agent-cockpit.

Agent Cockpit is a local whiteboard plus an MCP server for AI agents that do research. Any agent that speaks MCP (Claude Code, Codex, Cursor, Gemini CLI, …) draws its work onto the same board: the plan, the tasks, every experiment run, every claim, and the code each run depended on. A deterministic engine keeps checking the whole evidence chain. When any link changes, the cards that depend on it turn red. You can tell which results still hold, and why, without reading the code.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/chutingyean/Agent-Cockpit |
| GitHub stars | 501 |
| License | AGPL-3.0 |
| Language | JavaScript |
| Transport | stdio |
| Packages | npm: @tingyen/agent-cockpit |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Developer tools |
| Latest release | none |
| Last commit | Nov 6, 2026 |
| MCP registry name | io.github.chutingyean/agent-cockpit |

## Install

### Claude Desktop (claude_desktop_config.json)

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

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --transport stdio agent-cockpit -- npx -y @tingyen/agent-cockpit
```

### Cursor (.cursor/mcp.json)

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

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

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

Config formats checked against the official docs on 2026-10-07.

## Tools

- `cockpit_overview`: Call first: pending decisions, claims needing recheck and why, unreported changes
- `cockpit_task`: The agent's own task card, updated every round (what, why, next)
- `cockpit_run`: Run an experiment and record it
- `cockpit_claim`: Register a claim. Evidence must be a file and field written by a recorded run
- `cockpit_report`: Report which files changed
- `cockpit_review`: Code review: ocr if installed, otherwise built-in rules; or report your own findings

## Similar MCP servers

- [Notebooklm Skill](https://appsgit.com/mcp-servers/notebooklm-skill): NotebookLM does the research, Claude writes the content. (502 stars, MIT)
- [coolicons](https://appsgit.com/mcp-servers/coolicons): Search coolicons by meaning, then get SVG source and the right import in any style and radius. (497 stars, MIT)
- [NPMScan](https://appsgit.com/mcp-servers/npmscan): Detect malicious or vulnerable npm packages: registry search, OSV.dev and GitHub advisory lookups. (504 stars, MIT)
- [Entroly](https://appsgit.com/mcp-servers/entroly): Context Assurance for AI agents: context engineering, AI cost optimization, verification. (487 stars, Apache-2.0)
- [Vibe Check MCP Server](https://appsgit.com/mcp-servers/vibe-check-mcp-server): Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety. (506 stars, MIT, needs API key)
- [Code Context Engine](https://appsgit.com/mcp-servers/code-context-engine): Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. (461 stars, MIT)

---

Canonical page: https://appsgit.com/mcp-servers/agent-cockpit
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.
