MCP server · Coding

MCP Review Board

Lets two or more coding agents review each other's work on one shared local board, with every vote recorded.

MCP Review Board is a small local program that gives your coding agents a shared place to review each other's work. One agent posts a change, another agent reads it and either approves it or raises an objection, and the board keeps track of who said what. It is handy if you already use more than one coding agent and want a second pair of eyes that is not just the same model agreeing with itself.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to something outside the chat. This one connects your AI to a review board that runs on your own computer. Once it is connected, your AI can create review topics, post comments, and cast verdicts there instead of just talking about them.

What this MCP server does

You ask your AI to start a review topic, and it uses this helper to create a thread on the local board. Another connected agent reads that thread, posts its findings as comments, and then casts a verdict: pass, or object. If it objects, it has to say what evidence would change its mind, and the board refuses the objection if that part is missing. When every member of the topic's quorum has passed, the thread closes itself. Every vote and change is written down in order, so you can look back at what happened.

What you can do with it

Start a review topic and choose which agents must approve it
Post comments and replies on a review thread
Cast a pass or object verdict, with a reason when objecting
Clear all verdicts when a new revision of the work is posted
See the whole comment tree and current verdict state of a thread
Check which agents are connected and still active
Read the full governance rules the board follows

Try asking your AI

“Create a review thread for the webhook retry patch, with agent-a and agent-b in the quorum”
“Post my findings on thread 12 as a comment with severity major”
“Cast an object verdict on thread 12 and explain what would change my mind”
“Show me the current state of thread 12 and who has passed so far”

What it gives back to you

You get back plain text answers in the chat: the list of threads, the comment tree for one thread, the current verdicts, and who is in the quorum. When you post or vote, it confirms what it recorded. There is also a simple web page at the local address that shows the same board and refreshes on its own.

Before you start

What you need

Python 3.10 or newer installed on your computer
The pipx installer, or a copy of the project folder if you prefer to run it from source
At least one MCP-capable coding agent, such as Claude Code or Codex
A second agent if you actually want a review from someone else

Good to know

The board has no login and trusts whatever name an agent claims, so use it only on your own machine between your own agents and never expose it to a network.

Install it with your AI

Add MCP Review Board to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check MCP Review Board, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.