codereview-mcp
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 the latest commit diff"
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.
codereview-mcp
An MCP server that lets an AI coding agent review code with a language model. Point it at a git diff, a file, or a snippet and it returns a structured review with severity levels. It works with any MCP client (Claude Code, Cursor, VS Code, Continue, Windsurf) and supports Ollama (local, the default), OpenAI, Anthropic, OpenRouter, and any OpenAI-compatible server (llama.cpp, vLLM, LM Studio, and similar).
With the default Ollama backend, code never leaves your machine.
What it does
Reviews
git diffoutput, parsing it per file and skipping binaries and deletionsReviews whole files, with language auto-detected from the extension (50+ languages)
Reviews inline snippets in a language you specify
Returns findings tagged by severity: CRITICAL, WARNING, SUGGESTION, NOTE
Retries transient provider failures (rate limits, timeouts, 5xx) with backoff
It is a reviewer, not a gate. The output is advice from a model and should be read by a human, not wired straight into an automatic merge. See SECURITY.md for the threat model, including prompt injection.
Related MCP server: AI-PR-Review-MCP
Install
Requires Python 3.10+. Install from the repository:
pip install git+https://github.com/lfylow/codereview-mcpOr from a clone:
git clone https://github.com/lfylow/codereview-mcp
cd codereview-mcp
pip install .For the default local backend, install Ollama and pull a model. A coding-tuned model gives noticeably better reviews than a small general model:
ollama pull qwen2.5-coder:7b # recommended
# or the smaller default, lighter on RAM:
ollama pull llama3.2:3bThen run the server (it speaks MCP over stdio, so it's normally launched by a client rather than by hand):
codereview-mcp --model qwen2.5-coder:7bTo see which models are installed on your Ollama server:
codereview-mcp --list-modelsConnect an agent
Claude Code
claude mcp add codereview-mcp -- codereview-mcpTo use a hosted provider, pass the environment through:
claude mcp add codereview-mcp --env LLM_PROVIDER=openai --env OPENAI_API_KEY=sk-... -- codereview-mcpVS Code (Copilot) — .vscode/mcp.json
{
"servers": {
"codereview-mcp": { "type": "stdio", "command": "codereview-mcp" }
}
}Cursor — .cursor/mcp.json
{
"mcpServers": {
"codereview-mcp": { "command": "codereview-mcp" }
}
}Continue / Windsurf
Both use the same shape as Cursor: an mcpServers entry with "command": "codereview-mcp".
Add provider keys under an "env" object on that entry if you aren't using Ollama.
Once connected, ask the agent things like "review my staged changes" or "review
src/auth.py" and it will call the matching tool.
Tools
Tool | Use it for |
| Output of |
| A file on disk. Language detected from the extension. |
| A piece of code not yet in a file. |
Providers
Provider | Set | Connection | Notes |
Ollama |
| local server, no key | Code stays on your machine |
OpenAI |
|
| Also any OpenAI-compatible API via |
Anthropic |
|
| |
OpenRouter |
|
| One key, many models — see openrouter.ai/models |
OpenAI-compatible (llama.cpp, vLLM, LM Studio) |
| usually no key | Local servers generally ignore the key |
Authentication is by API key. The hosted providers don't offer an official way to use an account subscription in place of an API key for programmatic API access, so that mode isn't supported.
# OpenRouter
LLM_PROVIDER=openrouter OPENROUTER_API_KEY=sk-or-... codereview-mcp
# local OpenAI-compatible server (e.g. LM Studio on :1234), no key needed
LLM_PROVIDER=openai OPENAI_BASE_URL=http://localhost:1234/v1 codereview-mcp --model my-local-modelModels
Review quality tracks the model. For local use, a coding-tuned model is worth the extra download:
Model | Pull with | Notes |
Qwen2.5-Coder |
| Strong all-round code model; |
Qwen3-Coder |
| Newer Qwen coding model |
DeepSeek-Coder V2 |
| Good multi-language coverage |
Codestral |
| Mistral's code model |
CodeLlama |
| Widely available baseline |
Llama 3.2 3B |
| The default — small and fast, lighter reviews |
Run codereview-mcp --list-models to see what's installed locally. Pick a model with
--model, OLLAMA_MODEL, or the config file.
Configuration
Configuration is read from defaults, then a config file, then environment variables, then CLI flags — each layer overriding the previous one.
Environment variables
Variable | Default | Description |
|
|
|
|
| Ollama server URL |
|
| Ollama model name |
| — | OpenAI API key (optional for local servers) |
|
| OpenAI model name |
| — | Custom OpenAI-compatible endpoint |
| — | Anthropic API key |
|
| Anthropic model name |
| — | OpenRouter API key |
|
| OpenRouter model slug |
|
| OpenRouter endpoint |
|
| Max tokens per response |
|
| Sampling temperature (0–2) |
|
| Per-request timeout in seconds |
|
| Reject inputs larger than this |
|
| Stream responses; falls back to a single request if unsupported |
| — | Override the review prompt (must contain |
Config file
~/.config/codereview-mcp/config.yml on Linux/macOS (respects XDG_CONFIG_HOME),
or %APPDATA%\codereview-mcp\config.yml on Windows:
llm_provider: ollama
ollama_model: llama3.2:3b
temperature: 0.2
max_tokens: 2048CLI flags
codereview-mcp --help
codereview-mcp --version
codereview-mcp --provider openai --model gpt-4o
codereview-mcp --config /path/to/config.yml
codereview-mcp --list-models # list installed Ollama models and exit
codereview-mcp --no-stream # disable streaming
codereview-mcp --verboseExample output
A review of a small Python file looks like this:
## Review: `src/database.py` (python)
🔴 CRITICAL — SQL injection
`f"SELECT * FROM users WHERE id = {user_id}"` interpolates user input into SQL.
Use a parameterized query: `cursor.execute("SELECT * FROM users WHERE id = ?", (user_id,))`
🟡 WARNING — connection never closed
The connection opened on line 2 is never closed. Use a context manager:
`with sqlite3.connect("users.db") as conn:`
🟢 SUGGESTION — use the built-in
`calculate_average` can be `sum(numbers) / len(numbers)`.The exact wording depends on the model you run.
Troubleshooting
"connection refused" / transport errors — Ollama isn't running or isn't on the
expected URL. Start it with ollama serve and check OLLAMA_BASE_URL.
Empty or low-quality reviews — small local models miss things. Try a larger model
(OLLAMA_MODEL=qwen2.5-coder:7b) or a hosted provider.
"Input too large" — the file or diff exceeds MAX_INPUT_CHARS. Review a smaller
chunk or raise the limit.
"API key is required" — set OPENAI_API_KEY or ANTHROPIC_API_KEY for the chosen
provider.
Run with --verbose to see what the server is doing on stderr.
Limitations
Review quality depends entirely on the backing model. Small local models are fast and private but less thorough than large hosted ones.
The tool reviews the added/changed lines of a diff with surrounding context, not the full repository, so it can miss issues that span files.
Output is non-deterministic and advisory. It is not a substitute for tests or human review.
Development
git clone https://github.com/lfylow/codereview-mcp
cd codereview-mcp
pip install -e ".[dev]"
pytest
ruff check src/ tests/
ruff format --check src/ tests/
mypySee CONTRIBUTING.md for more.
License
MIT — see LICENSE.
Available Tools
3 toolsreview_code_fileB
Review an entire source file for bugs and improvements.
Provide the absolute path to a file. Language is auto-detected from the file extension. Supports 50+ languages.
Best for: reviewing new files, complete rewrites, or files where you want a comprehensive analysis of the entire codebase.
Inputs: filepath (required). Returns: result
review_code_snippetA
Review a code snippet (not from a file) in the specified language.
Use this when you have a small piece of code to review that isn't in a file yet, or when you want to review an isolated snippet.
Args: code: The source code to review. language: Programming language (python, javascript, rust, go, etc.)
Inputs: code (required), language. Returns: result
review_git_diffA
Review a git diff for bugs, security issues, and improvements.
Accepts the output of git diff as plain text. Returns a structured
review with severity levels (🔴 CRITICAL, 🟡 WARNING, 🟢 SUGGESTION, ℹ️ NOTE).
Example: git diff | review_git_diff
Inputs: diff (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct input type: file, snippet, or git diff. The descriptions clearly differentiate them, leaving no ambiguity about when to use each.
All tools follow the consistent 'review_<source>' pattern (review_code_file, review_code_snippet, review_git_diff), making naming predictable and clear.
Three tools is appropriate for the code review domain, covering the main scenarios without being too few or too many.
The surface covers the primary use cases: reviewing files, snippets, and diffs. Potential additions like reviewing a pull request or URL are missing but not essential.
Maintenance
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
Official Duck Framework MCP server for AI-assisted development and project scaffolding.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides agentic code review powered by OpenAI-compatible models, designed for use with Claude Code.1MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that automates pull request reviews using multiple LLM providers (OpenAI, Claude, Gemini, Groq, Perplexity) and supports GitHub and Bitbucket with real-time webhook integration and interactive AI assistant commands.1-
- AlicenseNot gradedqualityDmaintenanceMCP server for reviewing code changes using LLMs, supporting Copilot, Ollama, and OpenAI-compatible endpoints.MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for automated code review using AI agents. It analyzes code diffs or file paths for bugs, security issues, and style violations.MIT