Reported News
Agent Cockpit 0.1.0: evidence-chain whiteboard MCP for research agents
Agent Cockpit is an AGPL-3.0 open-source local whiteboard plus MCP server for research agents. Its README says it is "a local whiteboard plus an MCP server for AI agents that do research," and npm published @tingyen/agent-cockpit 0.1.0 on November 6, 2026, requiring Node.js 22.13+.
- Changes reported
- 5
- listed below, each from a source we read
- We tested
- Not tested yet
- reported from sources; we did not run it ourselves
- Gaps we flag
- 3
- things we could not verify
- Sources
- 3
- 3 primary, linked below
What changed
| # | What the source says | Status |
|---|---|---|
| 01 | The GitHub repository was created on October 26, 2026. On November 6, 2026 npm published @tingyen/agent-cockpit 0.1.0 (after a 0.0.0-stage tag the same morning), and the MCP Registry listed io.github.chutingyean/agent-cockpit as active. | Reported |
| 02 | The README describes a local whiteboard plus MCP server: any MCP agent (Claude Code, Codex, Cursor, Gemini CLI and others) draws plans, tasks, experiment runs and claims onto one board, and a deterministic engine flags cards when an evidence-chain link changes. | Reported |
| 03 | Evidence is hash-based: each run records hashes of its script, dependent files and reachable functions; if any of those change, the run goes stale and claims built on it are flagged for recheck. Reverting restores the hashes. | Reported |
| 04 | Quick start requires Node.js 22.13+ (for built-in node:sqlite), git and python3 for the demo. Install paths include npx -y @tingyen/agent-cockpit, a global cockpit CLI, and a Claude Code plugin marketplace entry. | Reported |
| 05 | Unreported file changes block git commit, and the board binds to 127.0.0.1 with no LLM calls in the checks. License is AGPL-3.0-or-later; GitHub showed 363 stars and 6 forks when we fetched the repo. | Reported |
reported by the sourcemeasured or run by usnot verified
Primary source: Agent Cockpit repository and README (GitHub). We are the fast, independent index; the vendor’s own page is the source of record for this release.
In the source’s words
“Agent Cockpit is a local whiteboard plus an MCP server for AI agents that do research.”
“Requires Node.js 22.13+ (for the built-in node:sqlite), git, and python3 for the demo project.”
“The MCP server is also listed in the MCP Registry as io.github.chutingyean/agent-cockpit.”
What we have not verified
- We did not install Agent Cockpit, run the demo, or connect it to Claude Code, Codex, Cursor or Gemini CLI.
- We did not verify that unreported changes always block git commit or Claude Code turn ends, or that the board stays local-only under all configs.
- Star and fork counts are a snapshot from GitHub at fetch time and can change.
This brief is Reported: written from the sources below, not from running the release ourselves.
Sources
- Agent Cockpit repository and README (GitHub)primary source · fetched 2026-11-06
- npm registry metadata for @tingyen/agent-cockpitprimary source · fetched 2026-11-06
- MCP Registry listing for io.github.chutingyean/agent-cockpitprimary source · fetched 2026-11-06
Related
Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/agent-cockpit-0-1-0-evidence-chain-mcp.md
Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.
Newsletter
The Weekly Verdict. Free, every Monday.
A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.
Free. Double opt-in. One click to unsubscribe.