Skip to main content
Glama

tai-mcp-github

A minimal MCP (Model Context Protocol) server that exposes a focused set of GitHub PR review tools to AI agents.

Why

The official github/github-mcp-server exposes 60+ tools (Actions, Discussions, Dependabot, secret scanning, gists, etc.). This inflates the MCP schema sent to the LLM on every request, increasing token usage and noise. This server limits the surface to exactly what is needed for a PR review workflow — nothing more.

Related MCP server: GitHub MCP Agent Server

Tools

Tool

Description

list_pull_requests

List open (or closed/all) PRs for a repository

get_pull_request

Get full details of a specific PR

list_pr_comments

List general thread comments on a PR (conversation tab)

list_unresolved_review_threads

List unresolved inline review threads (diff comments)

resolve_review_thread

Mark an inline review thread as resolved

Requirements

  • Python 3.12+

  • uv

  • A GitHub Personal Access Token with Pull requests: Read (and Write if you want to resolve threads)

Setup

git clone <repo-url>
cd tai-mcp-github

cp .env.example .env
# Edit .env and set GITHUB_TOKEN=your_pat_here

Usage

Run the server

uv run server.py

Use with Claude Code

Add to your MCP configuration (e.g. ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "github-pr-review": {
      "command": "uv",
      "args": ["run", "server.py"],
      "cwd": "/path/to/tai-mcp-github"
    }
  }
}

Development

Run tests

uv run --with pytest --with pytest-asyncio pytest tests/ -v

Lint and type-check

uv run --with ruff ruff check .
uv run --with ruff ruff format --check .
uv run --with mypy mypy server.py

Git hooks

Pre-commit (ruff + mypy) and pre-push (tests) hooks are provided. Install them once:

cp .git/hooks/pre-commit .git/hooks/pre-commit  # already in place after clone

Note: git hooks are local only. Run the script below on a fresh clone to activate them.

chmod +x .git/hooks/pre-commit .git/hooks/pre-push

Tech stack

  • fastmcp — MCP server framework

  • PyGithub — GitHub REST API client

  • httpx — HTTP client used for GitHub GraphQL API calls

  • python-dotenv — .env file support

  • ruff — linting and formatting

  • mypy — static type checking

  • pytest — testing

Architecture

server.py          # Single-file MCP server — all tools live here
tests/
└── test_server.py # Unit tests (fully mocked, no GitHub calls)

The server is intentionally stateless — no caching, sessions, or background tasks. Each tool maps directly to one GitHub API call:

  • PR listing and detail use the GitHub REST API via PyGithub

  • Review thread listing and resolving use the GitHub GraphQL API via a single httpx POST (the GraphQL resolveReviewThread mutation is not available on the REST API)

Authentication is via a GitHub Personal Access Token passed through the GITHUB_TOKEN environment variable. No OAuth or GitHub App flows are needed.

Scope

This server is read-focused. Explicitly out of scope:

  • Git operations (commits, pushes, branch management) — do these locally

  • Any GitHub feature outside the PR review workflow (Actions, Issues, Releases, etc.)

Available Tools

5 tools
get_pull_requestA

Get full details of a specific pull request.

Args: owner: Repository owner. repo: Repository name. pr_number: Pull request number.

Inputs: repo (required), owner (required), pr_number (required). Returns: result

list_pr_commentsA

List general thread comments on a pull request (conversation tab).

These are top-level comments, not inline review comments on the diff. Use list_unresolved_review_threads for inline code review comments.

Args: owner: Repository owner. repo: Repository name. pr_number: Pull request number.

Inputs: repo (required), owner (required), pr_number (required). Returns: result

list_pull_requestsB

List pull requests for a repository.

Args: owner: Repository owner (user or organisation). repo: Repository name. state: Filter by state — 'open' (default), 'closed', or 'all'.

Inputs: repo (required), owner (required), state. Returns: result

list_unresolved_review_threadsA

List unresolved inline review threads on a pull request.

Returns only threads that have not been resolved yet, so the agent has a clear picture of what still needs attention. Each thread includes its GitHub node ID (thread_id), file path, line number, and all comments. Pass thread_id to resolve_review_thread to mark a thread as done.

Args: owner: Repository owner. repo: Repository name. pr_number: Pull request number.

Inputs: repo (required), owner (required), pr_number (required). Returns: result

resolve_review_threadA

Mark a pull request review thread as resolved.

Use list_unresolved_review_threads to get thread_id values.

Args: thread_id: GitHub GraphQL node ID of the review thread.

Inputs: thread_id (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of pull request workflows: listing PRs, getting a specific PR, listing comments, listing unresolved review threads, and resolving them. There is no overlap or ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (list_pull_requests, get_pull_request, list_pr_comments, list_unresolved_review_threads, resolve_review_thread), using lowercase with underscores.

    Tool Count5/5

    Five tools is an appropriate and focused scope for a GitHub pull request review assistant. Each tool earns its place, covering listing, detail, comment viewing, unresolved thread viewing, and resolution.

    Completeness4/5

    The tool set covers the core PR review workflow well—listing, reading, and resolving threads. However, it lacks tools to create or reply to comments or threads, which agents may need to fully participate in reviews.

    Related MCP Connectors

    Related MCP Servers