Agent Cockpit
MCP server by chutingyean
Track AI research work on a local evidence-chain whiteboard where every claim traces back to its run and code.
Install Agent Cockpit
Runs on your machine. Your client starts it with this command:
Needs Node.js on your computer. The setup steps below show where the command goes in each client.
Share this server
Opens this page, with the install command and setup steps.
mcp.tc/i/agent-cockpitAbout
Agent Cockpit is a local whiteboard plus an MCP server for AI agents doing research. Agents such as Claude Code, Codex, Cursor and Gemini CLI record plans, tasks, experiment runs, claims and the code each run depended on. A rule-based engine checks the evidence chain by file hashes, and claims are flagged for recheck when something they rely on changes.
It runs locally over stdio through the npm package @tingyen/agent-cockpit, started with npx. It needs Node.js 22.13 or newer and a git repository. The board binds to 127.0.0.1. No sign-in or API key is needed, and checks make no LLM calls.
What you can do
- Record research plans, stages and task cards on a shared board
- Run experiments and record the script and dependency hashes
- Register claims backed by values written by recorded runs
- Flag claims for recheck when code or files change
- Ask a human for decisions and read the answers
- Run code review and report changed files
- Inspect code graph, impact analysis and architecture diagrams
Tools
Local servers list their tools once they’re running, and this one doesn’t publish its list in advance. Your client shows them after you add it.
Example prompts
Show the cockpit overview and tell me which claims need a recheck.
Run train.py through the cockpit and register a claim from its results.
Which files changed without being reported since the last run?
Ask me whether to restore the grader change that broke claim 3.
Set up
Every client starts Agent Cockpit on your machine with the same command. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport stdio agent-cockpit -- npx -y @tingyen/agent-cockpit mcp- Start Claude Code and type
/mcp. agent-cockpit should show as connected.
Add --scope user to make it available in every project.
Claude Desktop
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"agent-cockpit": {
"command": "npx",
"args": [
"-y",
"@tingyen/agent-cockpit",
"mcp"
]
}
}
}- Save the file and restart Claude Desktop.
Needs Node.js on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"agent-cockpit": {
"command": "npx",
"args": [
"-y",
"@tingyen/agent-cockpit",
"mcp"
]
}
}
}Needs Node.js on your computer.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"agent-cockpit","type":"stdio","command":"npx","args":["-y","@tingyen/agent-cockpit","mcp"]}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"agent-cockpit": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@tingyen/agent-cockpit",
"mcp"
]
}
}
}Needs Node.js on your computer.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"agent-cockpit": {
"command": "npx",
"args": [
"-y",
"@tingyen/agent-cockpit",
"mcp"
]
}
}
}- Refresh the MCP server list in Cascade.
Devin Desktop is the new name for Windsurf.
Codex
codex mcp add agent-cockpit -- npx -y @tingyen/agent-cockpit mcpOr edit ~/.codex/config.toml directly:
[mcp_servers.agent-cockpit]
command = "npx"
args = ["-y", "@tingyen/agent-cockpit", "mcp"]Needs Node.js on your computer.
Gemini CLI
gemini mcp add agent-cockpit npx -- -y @tingyen/agent-cockpit mcpThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients that start local servers accept this shape:
{
"mcpServers": {
"agent-cockpit": {
"command": "npx",
"args": [
"-y",
"@tingyen/agent-cockpit",
"mcp"
]
}
}
}Zed puts servers under context_servers in its settings, with the same command, args and env fields.
Needs Node.js on your computer.
Embed
Show Agent Cockpit in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/agent-cockpit)<a href="https://mcp.tc/i/agent-cockpit"><img src="https://mcp.tc/i/agent-cockpit/badge.svg" alt="Agent Cockpit on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/agent-cockpit.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/agent-cockpit" title="Agent Cockpit on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/agent-cockpit.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Agent Cockpit card to your site.
Add the mcp.tc card for Agent Cockpit, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/agent-cockpit.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="agent-cockpit"><a href="https://mcp.tc/i/agent-cockpit">Agent Cockpit on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/agent-cockpit)
```
Reference: https://mcp.tc/embedChange history
This server runs on your computer, so we follow its npm package: each new version shows up here, with edits by its owner.
FAQ
Can I paste mcp.tc/i/agent-cockpit into my MCP client?
No. Agent Cockpit runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is npx -y @tingyen/agent-cockpit mcp.
Does Agent Cockpit need an API key?
No. It doesn’t declare any keys or environment variables. It runs with your user account’s permissions, so check what its tools can reach.
Is Agent Cockpit a remote or a local server?
Local. Your client starts it as a process on your computer with npx -y @tingyen/agent-cockpit mcp, which needs Node.js.
What can Agent Cockpit do?
You can record research plans, stages and task cards on a shared board, run experiments and record the script and dependency hashes and register claims backed by values written by recorded runs.
Which clients can use it?
Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.
Does mcp.tc track changes to Agent Cockpit?
Partly. It runs on your computer, so we follow its npm package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Agent Cockpit’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with chutingyean. This page was built from Agent Cockpit’s public metadata, last checked on 15 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.