Governance rail for Claude Code — every AI coding agent on one board, with a tamper-evident event ledger.
Run more than one AI coding agent on a machine and a familiar problem appears: nobody can say with confidence what each one touched, when it started, whether it is still running, or what it cost. The flightdeck mcp server exists to answer those questions. It dispatches every Claude Code agent onto a single board and records what happens in a hash-chained event ledger, so the history of a session is something you can audit rather than reconstruct from memory.
FlightDeck is built around a small set of governance ideas that show up directly in how it behaves:
That last detail is a good signal of the project's temperament. Treating an unmeasured cost as zero makes dashboards look tidy and makes them wrong; FlightDeck would rather show you a gap.
The server ships on PyPI as flightdeck-connect and runs through uvx, so there is no build step and nothing to keep patched by hand. If you already use uv, uvx --from flightdeck-connect conductor-mcp cold-boots the server and serves its full tool set. Without uv, a one-off pip install flightdeck-connect and a config block pointing at conductor-mcp gets you the identical server.
As a Claude Code plugin there is a shorter path — add the marketplace, install the plugin, and /flightdeck turns governance on inside a session. Point FLIGHTDECK_BOARD at a folder and you are running; a board is just a local directory, created the first time you make a packet.
Most MCP servers add a capability — a database to query, a browser to drive, an API to call. FlightDeck does something different: it watches the agents you already have. That makes it a poor first server to install and a sensible one to add the moment you are running several agents in parallel and have started losing track of which did what.
It is worth being clear about the trade-off. The package is proprietary rather than open source — free to install, with a patent pending — so it sits differently from the MIT-licensed tooling that surrounds most of this ecosystem. On the other hand, the board is local-first: the board tools send nothing anywhere, and the cloud family stays inert without an operator-issued token, which is a meaningful posture for something observing your engineering work.
uv on PATH for the recommended install route.Reconstruct what each agent did from a tamper-evident ledger instead of scrollback.
Claim adjudication decides which agent holds a piece of work when two reach for it.
Unknown spend is recorded as unknown rather than counted as zero, so gaps stay visible.
| Tool | What it does |
|---|---|
| flightdeck_create_packet | Create a work packet on the board — this also creates the board folder on first run. |
/plugin marketplace add NorthGate-Strategic-LLC/flightdeck-pluginThen run /plugin install flightdeck@flightdeck, and /flightdeck in any session to turn governance on.
Python 3.9 or newer. uv on PATH for the uvx install route, or install flightdeck-connect from PyPI with pip and run conductor-mcp directly.
| Variable | Description | Required |
|---|---|---|
| FLIGHTDECK_BOARD | Folder the board is kept in. A board is a plain local directory, created on first use. | Optional |
| MCP_TOOL_SET | Selects the tool set the server exposes; set to flightdeck for the governance board. | Optional |
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.
Errors with full context — stack traces, issue triage and AI-powered root-cause analysis from Sentry's server.
Enables enhanced web research capabilities for large language models through intelligent search queuing and advanced content extraction.
Automates browser interactions and enables Large Language Models (LLMs) to interact with web pages through Playwright and Chrome DevTools Protocol
Guides tool usage by providing recommendations for MCP tools at each problem-solving stage.