claudeers.
// MCP Servers

Agent-Cockpit

Evidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. 讓 AI agent 做研究時,每個結論都能追到產生它的程式碼。…

// MCP Servers[ cli ][ api ][ web ][ claude ]#claude#ai-agents#claude-code#code-review#codex#developer-tools#knowledge-graph#mcp#mcp-servers◷ AGPL-3.0$open-sourceupdated 14 days ago

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up Agent-Cockpit (claude-plugin project) into my current project.
Found on https://claudeers.com/agent-cockpit
Repo: https://github.com/chutingyean/Agent-Cockpit
Homepage/docs: —
Detected install method: claude-plugin → /plugin install agent-cockpit@chutingyean/Agent-Cockpit
Category: mcp-servers. Platforms: cli, api, web.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
unknown; community-verified: false. Confirm the source before running anything.
// or install directly (claude-plugin)

⚠ Unverified / not recently updated — review before pasting a run-this config.

/plugin marketplace add chutingyean/Agent-Cockpit
/plugin install agent-cockpit@chutingyean/Agent-Cockpit
// or clone
git clone https://github.com/chutingyean/Agent-Cockpit

// compatibility

Platformscli, api, web
Operating systems—
AI compatibilityclaude
LicenseAGPL-3.0
Pricingopen-source
LanguageJavaScript

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

Agent Cockpit: every research claim, traceable to the code that produced it

English · 繁體中文

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.

Replaying a real session: two agents complete a study, an unreported change breaks one claim, a human decides, an agent restores it

Replay of a real session: Claude Code and Codex complete a small study from an empty repo. An unreported edit breaks one claim, and the cockpit raises a decision and writes a brief. A human picks "restore", and an agent carries it out.

Why

After a few days of research with AI agents, the same things keep going wrong:

  • Claims lose their footing silently. An agent edits the grader, the data pipeline or a statistics helper, and results that were "verified" no longer hold. Nobody notices.
  • Changes go unreported. Files change and no agent says so, or an agent says it changed something it didn't.
  • Decisions pile up, assumptions harden, loops spin. Questions meant for a human wait unanswered, untested premises become foundations, and an agent keeps tweaking hyperparameters "one more time".
  • The code grows faster than you can read it.

Agent Cockpit turns these into rules a machine can check, and shows the result on one board.

Features

  • Evidence chains, down to a JSON field. A claim must cite a value that a recorded run actually wrote. Each run records the hash of its script, of every file the script depends on, and of each function it reaches. If any of those changes, the run goes stale and every claim built on it is flagged for recheck. Revert the change and the hashes match again, so the claims recover.
  • Works with any MCP agent. Agent identity comes from the MCP handshake. cockpit init writes the config for Claude Code, Cursor, VS Code and Gemini CLI, and prints the command for Codex.
  • One write gate. Every write from MCP, the CLI or the board passes through the same validator. Non-compliant writes are rejected with a reason the agent can act on. Rejections are logged too.
  • Unreported changes get caught. Real file changes are detected whether or not an agent reports them. Unreported changes block git commit, and Claude Code cannot end its turn until it reports them.
  • Built-in code graph and code review, no extra installs. A lightweight graphify-style call graph supplies dependency closures, communities, core nodes and impact analysis. A rule-based reviewer looks at the changed lines every time a file changes. Install the real graphify or open-code-review and they are used automatically.
  • Human decisions in the loop. Agents ask through cockpit_decide and wait. When a change breaks claims, the cockpit raises a decision itself and writes a one-page evidence brief, laid out by answer-me-with-html.
  • Replay. Everything is an append-only event, so you can scrub or play the board back to any moment. A brief stays available even after the problem is fixed.
  • Local and deterministic. The board binds to 127.0.0.1. Every check is a plain rule, with no LLM calls and zero tokens.

Quick start

Requires Node.js 22.13+ (for the built-in node:sqlite), git, and python3 for the demo project.

git clone https://github.com/chutingyean/Agent-Cockpit.git
cd Agent-Cockpit
npm install
npm run demo                                       # build a demo research repo: 6 real runs, 6 claims
node bin/cockpit.mjs serve --repo demo/research    # open http://127.0.0.1:4180

Then, in a second terminal, break something and watch the board:

node bin/cockpit.mjs demo --break      # quietly loosens the grader's answer matching, unreported
node bin/cockpit.mjs demo --restore    # put it back: hashes match, claims recover

The board after the grader was changed: dependent claims turn red, the cockpit raises a decision

Use it on your own research repo

No clone needed:

cd /path/to/your-research                                   # must be a git repo
npx -y @tingyen/agent-cockpit init                      # MCP configs, AGENTS.md, Stop hook, pre-commit
npx -y @tingyen/agent-cockpit serve                     # the board
npx -y @tingyen/agent-cockpit run -- python3 train.py   # run experiments through the cockpit

Prefer a permanent cockpit command? npm install -g @tingyen/agent-cockpit.

init only writes inside your repo. Open the repo in your agent and it reads AGENTS.md and the MCP config. The tutorial walks through every agent step by step.

Claude Code plugin. Adds a skill that teaches Claude when and how to use Agent Cockpit, including how to set it up:

claude plugin marketplace add chutingyean/Agent-Cockpit
claude plugin install agent-cockpit@agent-cockpit

The same skill lives in skills/agent-cockpit/SKILL.md for other agents that read SKILL.md files. The MCP server is also listed in the MCP Registry as io.github.chutingyean/agent-cockpit.

How it works

The evidence graph: claim → run → code → architecture layer, with review, summaries and briefs as annotations

  • Content hashes, not timestamps. Staleness is decided by comparing hashes, so reverting a file restores validity exactly.
  • Function-level precision. For Python dependencies, a change to a function the run never reaches does not make the run stale. Changes to reachable functions, imports or module-level code always do.
  • Event sourcing. .cockpit/events.jsonl is the single source of truth, and it doubles as the agents' work log. Commit it. The board is a pure projection (reduce → derive), which makes replay possible.

Architecture: agents, CLI and the board all write through one gate into an append-only event store; the engine projects it onto the board

MCP tools

Research toolsPurpose
cockpit_overviewCall first: pending decisions, claims needing recheck and why, unreported changes
cockpit_plan / cockpit_stageThe research path. A stage cannot close until its required tools have been called
cockpit_taskThe agent's own task card, updated every round (what, why, next)
cockpit_runRun an experiment and record it
cockpit_claimRegister a claim. Evidence must be a file and field written by a recorded run
cockpit_hypothesis / cockpit_premiseHypotheses and not-yet-verified premises
cockpit_decide / cockpit_decisionsAsk a human; read the answers
cockpit_reportReport which files changed
cockpit_reviewCode review: ocr if installed, otherwise built-in rules; or report your own findings

Canvas tools: canvas_list, canvas_read, canvas_search, canvas_createNode, canvas_link, canvas_diagram (architecture diagrams in md²'s format) and canvas_structure (code graph and impact analysis).

CLI

npm install -g @tingyen/agent-cockpit gives you a global cockpit command. Otherwise use npx -y @tingyen/agent-cockpit <command>, or node bin/cockpit.mjs from a clone.

CommandPurpose
cockpit initWrite MCP configs, rules files, the Stop hook and the pre-commit hook
cockpit serve [--port 4180]Open the board
cockpit run -- <command>Run and record an experiment
cockpit graphRebuild the code graph (graphify if installed)
cockpit review [--all]Code review (ocr if installed; changed lines by default)
cockpit status / cockpit checkPrint the cockpit summary / list unreported changes
cockpit demo [--break|--restore|--fresh]The demo project

Every command accepts --repo <path>; the default is the current directory.

Project layout

bin/cockpit.mjs      CLI
src/engine.mjs       reduce and derive: evidence chains, propagation rules, tours, brief drafts
src/gate.mjs         the single write gate
src/store.mjs        event store (node:sqlite) and canvas projection
src/run.mjs          cockpit run
src/graph.mjs        built-in code graph (graphify-compatible output)
src/review.mjs       built-in rule-based code review
src/mcp.mjs          MCP server
src/server.mjs       board server (SSE, decisions, briefs, replay)
web/board.html       the board (no framework, no build step)
demo/template/       demo research project (Python, really runs)
skills/              SKILL.md that teaches agents to work under Agent Cockpit
.claude-plugin/      Claude Code plugin and marketplace manifests
server.json          MCP Registry metadata
docs/                tutorial, figures, screenshots, a recorded real session
test/                node:test suite (npm test)

Documentation

  • Tutorial: from the demo to your own project, every agent, replay, and a recorded real session
  • Recorded session: the events, the code the agents wrote, and their output

Acknowledgements

Agent Cockpit fuses ideas from six projects into one evidence graph: research-cockpit (claims, hypotheses, premises, decisions), graphify (code graph), open-code-review (code review), Understand-Anything (summaries, layers, tours, personas), md² (architecture diagram format) and answer-me-with-html (one-page briefs). See THIRD_PARTY_NOTICES.md for what is bundled and under which license.

License

Copyright (C) 2026 chutingyean

Agent Cockpit is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. If you modify it and let others use it over a network, you must offer them the source code of your version. Third-party components keep their own licenses; see THIRD_PARTY_NOTICES.md.

// faq

What is Agent-Cockpit?

Evidence-chain whiteboard + MCP server for AI research agents: every claim traces back to the run and code that produced it. 讓 AI agent 做研究時,每個結論都能追到產生它的程式碼。Claude Code · Codex · Cursor · Gemini CLI. It is open-source on GitHub.

Is Agent-Cockpit free to use?

Agent-Cockpit is open-source under the AGPL-3.0 license, so it is free to use.

What category does Agent-Cockpit belong to?

Agent-Cockpit is listed under mcp-servers in the Claudeers registry of Claude-compatible tools.

9 views
★ 396 stars
unclaimed
updated 14 days ago

// embed badge

Agent-Cockpit on Claudeers
[![Claudeers](https://claudeers.com/api/badge/agent-cockpit.svg)](https://claudeers.com/agent-cockpit)

// retro hit counter

Agent-Cockpit hit counter
[![Hits](https://claudeers.com/api/counter/agent-cockpit.svg)](https://claudeers.com/agent-cockpit)

// reviews

// guestbook

0/500

// related in MCP Servers

🔓

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete…

// mcp-serversf/⟨HTML⟩★ 177,810◷ NOASSERTION[ claude ]
🔓

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

// mcp-serversfarion1231/⟨Rust⟩★ 155,814◷ MIT[ claude ]
🔓

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

// mcp-serversJuliusBrussee/⟨JavaScript⟩★ 117,780◷ MIT[ claude ]
🔓

An open-source AI agent that brings the power of Gemini directly into your terminal.

// mcp-serversgoogle-gemini/⟨TypeScript⟩★ 108,744◷ Apache-2.0[ claude ]
→ see how Agent-Cockpit connects across the ecosystem