agentleFS
Sign inStart free
folay-gitfolay-git/code-review-mcp/llms.txt

code-review-mcp

llms.txt4 starsChanged 11 months agoMITView on GitHub

MCP server that lets AI assistants review GitHub Pull Requests and GitLab Merge Requests. code-review-mcp is a Model Context Protocol (MCP) server for automated code review. It connects to GitHub and GitLab (including self-hosted GitLab), fetches PR/MR diffs, and exposes MCP tools for inline comments, batch comments, and custom project review rules. Works with Cursor, Claude Desktop, and any MCP-compatible client via stdio, SSE, or WebSocket. Set GITHUB_TOKEN and/or GITLAB_TOKEN (and GITLAB_HOST for self-hosted).

  • Reads credentials
  • Installs packages

The file

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Cursor setup: Add to ~/.cursor/mcp.json with command uvx and args ["code-review-mcp"]

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# Code Review MCP Server

> MCP server that lets AI assistants review GitHub Pull Requests and GitLab Merge Requests.

code-review-mcp is a Model Context Protocol (MCP) server for automated code review. It connects to GitHub and GitLab (including self-hosted GitLab), fetches PR/MR diffs, and exposes MCP tools for inline comments, batch comments, and custom project review rules. Works with Cursor, Claude Desktop, and any MCP-compatible client via stdio, SSE, or WebSocket.

## Documentation

- [README (English)](https://github.com/folay-git/code-review-mcp/blob/main/README.md): Full setup and configuration
- [README (中文)](https://github.com/folay-git/code-review-mcp/blob/main/README_CN.md): Chinese documentation
- [PyPI](https://pypi.org/project/code-review-mcp/): `pip install code-review-mcp` or `uvx code-review-mcp`

## MCP tools

- `get_review_rules` — builtin + custom project rules
- `get_pr_info` — PR/MR metadata
- `get_pr_changes` — diff with optional file-type filter
- `add_inline_comment`, `add_pr_comment`, `batch_add_comments` — post review feedback

## Quick start

```bash
uvx code-review-mcp
# or: pip install code-review-mcp && code-review-mcp
```

Set `GITHUB_TOKEN` and/or `GITLAB_TOKEN` (and `GITLAB_HOST` for self-hosted).

## Common questions

- **Cursor setup**: Add to `~/.cursor/mcp.json` with command `uvx` and args `["code-review-mcp"]`
- **Self-hosted GitLab**: Set `GITLAB_HOST=gitlab.yourcompany.com`
- **Custom rules**: `code-review-mcp init-rules` or `CODE_REVIEW_RULES_DIR`
- **Remote deploy**: `--transport sse` or `--transport websocket` on port 8000
- **License**: MIT

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free