Happy slice of mcp pizzaMCP.pizza

mission-control

MCP.Pizza Chef: builderz-labs

This self-hosted dashboard gives you a single home base for every AI agent you run, whether that's Claude Code, Codex, OpenClaw, or another coding assistant. You can hand out tasks, watch them move from assignment to review to done, catch failures before they cause problems, and see exactly how much each agent run is costing you. It runs on your own computer or server, connects through a small program you install with Docker or Node.js, and needs an API key for automated or script-based access.

Coding
Data

Use This MCP client To

See what all my AI coding agents are working on right now Assign a task to a specific AI agent Review an agent's completed work before approving it Track how much each AI agent run is costing me Get alerted when an agent run fails or needs review Keep a history of every task my agents have finished Coordinate several AI agents from one shared dashboard

README

Mission Control

Self-hosted control plane for operating AI agents.

Dispatch tasks, inspect runs, review failures, track spend, and coordinate agent runtimes from one local dashboard backed by SQLite.

An open-source project by Builderz Labs, created and maintained by nyk. It works with OpenClaw, Claude Code, Codex, and other runtimes - it is not part of any one of them.

Quality Gate Release License: MIT

Mission Control overview dashboard with active sessions, live activity, fleet status per runtime, and the task pipeline

Warning

Mission Control is alpha software. APIs, schemas, and configuration may change between releases. Read the security guidance before exposing it to a network.

Start locally

Node.js 22 or newer and pnpm are required for a source install.

git clone https://github.com/builderz-labs/mission-control.git
cd mission-control
bash install.sh --local

Open http://localhost:3000/setup, create the first admin account, then copy the API key from Settings if an agent or script needs headless access.

The manual path is useful when you already manage Node and pnpm:

nvm use 22
pnpm install
pnpm dev

Windows users can run ./install.ps1 -Mode local in PowerShell.

Start with Docker

docker compose up

Or run the published multi-architecture image:

docker pull ghcr.io/builderz-labs/mission-control:latest
docker run --rm -p 3000:3000 ghcr.io/builderz-labs/mission-control:latest

Use the hardened Compose overlay for a network-accessible deployment:

docker compose -f docker-compose.yml -f docker-compose.hardened.yml up -d

mission-control FAQ

Do I need to know how to code to use Mission Control?
You'll need some technical comfort — setting it up involves running a program on your own computer or server through Docker or Node.js, and it's built for people who already work with AI coding agents like Claude Code or Codex.
Can I use this to keep track of what my AI agents are doing?
Yes — Mission Control gives you one dashboard that shows every task, its current status, and which agent is handling it, so you're never left guessing.
Do I need an account or an API key?
Yes. You create an admin account the first time you run it, then copy an API key from your settings if you want an agent or script to connect automatically.
Which AI agents can I connect?
It's built to work with Claude Code, Codex, OpenClaw, and several other AI agent runtimes, so you can manage more than one type of AI helper from the same place.
Can I use this to track how much I'm spending on AI agents?
Yes — it includes a cost view that tracks token use and spending across all your connected agents.
Is my data sent to a third party?
No. Mission Control runs on your own computer or server and stores everything locally, so you stay in control of your data.
How hard is it to set up?
It takes some technical setup — you'll either run an installer script, use Docker, or install it manually with Node.js, so it's best suited to people comfortable with basic command-line steps.
Can I use this with more than one AI agent at a time?
Yes — it's built specifically for coordinating multiple agents, so you can see all of them together instead of switching between separate tools.