Provides tools for reviewing GitHub pull requests, including listing open PRs, fetching diffs, and submitting structured reviews (approve, comment, request changes) directly to GitHub.
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., "@MCP GitHub PR Reviewer review the diffs for PR #42 in acme/widgets"
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 locally hosted Model Context Protocol (MCP) server that enables AI assistants (like Claude Desktop and Cursor) to autonomously review GitHub Pull Requests.
list_prs: Fetches open pull requests for a given repository.
get_pr_diff: Retrieves the raw git diff of a specific PR.
submit_review: Posts structured reviews (APPROVE, COMMENT, REQUEST_CHANGES) directly to GitHub.
Dynamic Resource: Injects standard corporate code review guidelines into the AI's context window to standardize evaluations.
Related MCP server: GitHub PR Reviewer
Node.js & TypeScript
@modelcontextprotocol/sdk (Stdio Transport)
zod (Strict runtime schema validation)
GitHub REST API
This server acts as a bridge between an LLM and GitHub. Using the MCP standard, the AI can discover these tools, determine when to use them, validate the inputs via Zod schemas, and execute multi-step reasoning to read code and enforce review guidelines—all without human intervention.
This server cannot be deployed
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Read and write KukGit repositories, files, issues and pull requests from an AI assistant.
Access the GitHub API, enabling file operations, repository management, search functionality, and…
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
