Provides code review capabilities for GitHub pull requests (including GitHub Enterprise), including defect-oriented reviews, improvement suggestions, and posting review comments.
Provides code review capabilities for GitLab merge requests, including defect-oriented reviews, improvement suggestions, and posting review comments.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@codereview-mcp Review https://github.com/owner/repo/pull/123 and post the report as a comment"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A stateless MCP server that reviews, rates, and improves pull requests on demand — from any MCP client (Claude Code, Cursor, OMP, ...). Built on Streamable HTTP and deployable as a single container behind Nginx.
Most AI code-review bots hook into webhooks and CI pipelines. codereview-mcp flips the model: the review happens inside your AI client's conversation — you paste an MR/PR link, ask for a review, and get a structured report you can discuss, refine, and post back. The server holds no sessions and stores nothing, so it scales horizontally and leaves no trace.
Related MCP server: code-review-mcp-server
One URL in, one report out — the platform (GitLab / GitHub / GHE) is auto-detected from the URL shape; no per-repo setup.
Structured review — the LLM returns strict JSON (file / line / severity / suggestion); the Markdown report, risk rating, and Critical/High/Medium/Low statistics are rendered by code, never by the model.
Huge-MR protection — generated files (lockfiles, minified bundles, protobuf code) are filtered first; oversized diffs are split into chunks, reviewed concurrently (map-reduce), and merged. Everything filtered/truncated/dropped is stated honestly in the report's coverage notes.
Real-time progress — MCP progress notifications stream every stage (fetch → filter → LLM → merge).
Any OpenAI-compatible LLM — DeepSeek, Claude gateways, private vLLM / Ollama.
Defense-in-depth auth — static bearer token at the Nginx gateway plus an optional independent server-side token check.
Stateless Streamable HTTP — no sticky sessions; safe behind any load balancer.
Tool | What it does |
| Full defect-oriented review → Markdown report (summary, risk rating, findings sorted by severity, coverage notes). Optional |
| Non-defect improvement suggestions (refactoring, performance, testability, readability, security hardening) → Markdown report. |
| Post any Markdown back to the PR/MR as a comment; returns the comment URL. |
git clone https://github.com/lukaisluka/codereview-mcp.git
cd codereview-mcp
uv sync
cp .env.example .env
# edit .env: GitLab/GitHub token, LLM endpoint + key
uv run codereview-mcp # serves http://0.0.0.0:8000/mcpcp .env.example .env # fill in real values, incl. NGINX_AUTH_TOKEN
docker compose up -d --build # nginx gateway on http://<host>:8080The compose stack runs the service (memory-capped at 500 MB) behind an Nginx gateway that enforces the static bearer token and proxies SSE without buffering. Layered timeouts: Nginx 300 s → LLM 240 s → Git API 30 s, so the gateway is always the last to give up.
Point your MCP client at http://<host>:8080/mcp with header
Authorization: Bearer <NGINX_AUTH_TOKEN> — see examples/mcp-clients.md
for Claude Code / Cursor / generic JSON snippets and examples/python_client.py
for a programmatic client with progress callbacks.
All settings come from environment variables (or .env). Key ones:
Variable | Default | Description |
|
| Startup hint; actual routing follows the |
| — | GitLab root URL + token (API scope). |
|
| GitHub or GHE; token optional for public repos, required for writes/GHE. |
|
| Model name; a litellm-style |
| — | Any OpenAI-compatible endpoint. Key may be empty for intranet hosts (vLLM/Ollama). |
|
| Per-call LLM timeout (keep ≥ 180 and below the gateway's 300 s). |
|
| Huge-MR protection thresholds. |
|
|
|
| empty | Optional server-side bearer check (defense in depth; |
| — | Static bearer token enforced by the Nginx gateway (compose deployment). |
|
| Language for report prose (summary / descriptions). |
|
| Parallel chunk reviews in map-reduce mode. |
Full list with comments: .env.example
uv sync # install with dev group
uv run pytest # 90+ tests, fully mocked boundaries
uv run ruff check . # lint
uv run ruff format . # formatProject layout:
src/codereview_mcp/
├── config.py # env-driven settings (pydantic-settings)
├── server.py # FastMCP tools, bearer middleware, /health, entrypoint
├── git/ # URL parser, GitLab/GitHub clients, provider factory
└── review/ # diff protection, prompts, LLM client, JSON parsing,
# models, markdown rendering, orchestration serviceThis server cannot be deployed
A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management.…
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Read-only AI coding tools for change verification, release readiness, capacity, and guidance.
