AI coding assistants ship code fast. But someone still has to review it. I wanted that "senior engineer second pair of eyes" to live inside my editor, run entirely on my machine, and work with whatever assistant I'm using today. So I built MCP Code Review Server — a Model Context Protocol (MCP) server that connects to Claude Code, Cursor, Cline, or any MCP client.
It exposes three tools to your AI assistant:
review_code
— paste any snippet and get a structured reviewreview_diff
— review a git diff before you mergereview_file
— point it at a local fileEach review returns findings with severity ratings (Critical / High / Medium / Low), file locations, and concrete fix suggestions.
The checks are the ones I kept catching my own assistants missing:
No signup, no API keys. It's on PyPI:
claude mcp add code-review -- uvx aicraft-code-review
{
"mcpServers": {
"code-review": {
"command": "uvx",
"args": ["aicraft-code-review"]
}
}
}
pip install aicraft-code-review
That's it. Your assistant now has a review tool it can call whenever you ask.
I tried the hosted code-review tools first. They're good, but three things kept bothering me:
The server runs over stdio as a local process. Your code never leaves your machine. The only cost is the electricity.
A few things I'd do the same way again:
uvx
means users never even install it.review_diff
slots right into the "review before commit" habit that agents already have.Getting a server working is the easy part. Getting it found is the real work:
That's why I've been submitting the server to every directory with a review process, and keeping the repo metadata (glama.json
, .mcp.json
, smithery.yaml
, a Dockerfile
) in shape for their automated checks.
If you try it and hit a case it misses, open an issue — the rules are all configurable, and new checks are the fastest way this thing gets better.
What would you want an in-editor code reviewer to catch that yours currently misses?