tai-mcp-github
Provides tools for managing GitHub pull requests, including listing, viewing details, comments, and review threads.
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., "@tai-mcp-github List unresolved review threads in PR #42"
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.
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 open (or closed/all) PRs for a repository |
| Get full details of a specific PR |
| List general thread comments on a PR (conversation tab) |
| List unresolved inline review threads (diff comments) |
| Mark an inline review thread as resolved |
Requirements
Python 3.12+
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_hereUsage
Run the server
uv run server.pyUse 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/ -vLint and type-check
uv run --with ruff ruff check .
uv run --with ruff ruff format --check .
uv run --with mypy mypy server.pyGit 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 cloneNote: 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-pushTech stack
fastmcp — MCP server framework
PyGithub — GitHub REST API client
httpx — HTTP client used for GitHub GraphQL API calls
python-dotenv —
.envfile supportruff — 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
httpxPOST (the GraphQLresolveReviewThreadmutation 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 toolsget_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
Scored across 5 tools
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.
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.
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.
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
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
An MCP server that gives your AI access to the source code and docs of all public github repos
GitHub Copilot MCP: code, repo, PR, workflow tools for AI assistants.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables AI agents to retrieve detailed GitHub Pull Request information using git commit hashes, branch names, or PR numbers. It automatically detects repositories and extracts comprehensive PR data including descriptions, labels, and reviews via the GitHub CLI.16 npmISC
- AlicenseBqualityCmaintenanceMCP server that exposes GitHub operations as tools for AI agents, enabling code search, issue management, and PR review.1236 PyPIMIT
- FlicenseAqualityDmaintenanceAn MCP server exposing AI-powered GitHub PR review as tools.5-
- FlicenseAqualityDmaintenanceMCP server exposing GitHub tools for issues, pull requests, and code browsing via the GitHub REST API. Designed for local LLM clients with flat arguments and streamable HTTP support.15-