Connects to authenticated GitHub data via the GitHub REST API, providing tools for listing repositories, viewing open issues and pull requests, counting open issues across repositories, summarizing repository activity, detecting stale issues, and safely creating issues or adding labels after dry-run confirmation.
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., "@GitHub MCP Server show me the open issues labeled bug in my repo"
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 Model Context Protocol (MCP) server connecting AI assistants to authenticated GitHub data — repositories, issues, pull requests, and stale-backlog detection — via the GitHub REST API.
MCA Minor Project · VIPS-TC, GGSIPU, Delhi
┌──────────────────────────────────────────────────────┐
│ LOCAL MACHINE │
│ │
│ ┌──────────────┐ stdio (JSON-RPC) ┌──────────┐ │
│ │ MCP Client │ ◄══════════════════► │ server │ │
│ │ (Inspector) │ │ .py │ │
│ └──────────────┘ └────┬─────┘ │
│ │ │
│ HTTPS (REST) │
└─────────────────────────────────────────────┼───────┘
▼
┌─────────────────┐
│ api.github.com │
└─────────────────┘Principle | Implementation |
Read-only first | 5 of 7 tools are strictly read-only |
Safe writes |
|
Least privilege | Fine-grained PAT scoped to Issues + PRs + Metadata |
Protocol integrity | All logging → |
Related MCP server: GitHub MCP Server
# | Tool | Mode | Description |
1 |
| Read | Authenticated user's repositories with stars, forks, visibility |
2 |
| Read | Open issues for a repo; optional label filter; excludes PRs |
3 |
| Read | Cross-repo open-issue count via GitHub Search API |
4 |
| Read | Dashboard: repo metrics + recent commits + open PRs |
5 |
| Read | Issues with no activity for N days |
6 |
| Write | Creates issue after dry-run preview and explicit confirmation |
7 |
| Write | Adds labels to issue after dry-run preview and confirmation |
Python 3.10+
A GitHub account with a fine-grained Personal Access Token
git clone https://github.com/pranjay6667/github-mcp-server.git
cd github-mcp-server
python -m venv .venv
.venv\Scripts\activate # Windows
# source .venv/bin/activate # macOS / Linux
pip install -r requirements.txtCreate a fine-grained token at github.com/settings/personal-access-tokens/new
Permissions: Issues (Read & Write), Pull Requests (Read), Metadata (Read)
Copy .env.example → .env and paste your token:
GITHUB_TOKEN=github_pat_...mcp dev server.pyOpens a browser UI at localhost:6274 with all 7 tools ready to invoke.
Add to %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"github": {
"command": "C:\\path\\to\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\server.py"]
}
}
}Restart Claude Desktop. The tools icon will show 7 tools.
python tests/test_tools.py # All 7 tools against live API
python tests/test_safety.py # Dry-run vs confirmed execution
python tests/test_protocol.py # MCP JSON-RPC handshakeA 50-question benchmark (evaluation/questions.csv) across English, Hindi, and Hinglish tests tool-routing accuracy:
Round | Accuracy | Notes |
Round 1 (naive prompts) | 90.0% (45/50) | Boundary ambiguity in cross-repo queries |
Round 2 (refined prompts) | 98.0% (49/50) | Scope guards + negative constraints added |
Run the benchmark:
python evaluation/evaluate.pygithub-mcp-server/
├── server.py # MCP server — 7 tool definitions
├── github_client.py # GitHub REST API client
├── config.py # Token loader from .env
├── requirements.txt
├── .env.example
├── tests/
│ ├── test_tools.py # Tool integration tests
│ ├── test_safety.py # Dry-run confirmation tests
│ └── test_protocol.py # MCP handshake test
├── scripts/
│ └── seed_test_data.py # Creates sample issues/labels
├── evaluation/
│ ├── questions.csv # 50-question benchmark
│ ├── evaluate.py # Benchmark runner
│ └── results.csv # Round 1 & 2 results
└── docs/
├── PROJECT_REPORT.md
├── PPT_OUTLINE.md
├── DEMO_SCRIPT.md
├── VIVA_QUESTIONS.md
└── INTERVIEW_PITCH.mdNo hardcoded credentials — token loaded from .env via config.py
.env in .gitignore — never committed
Least privilege — PAT scoped to metadata, issues, and PRs only
No destructive tools — no deletion or repo-level mutation
Dry-run by default — write tools preview before executing
MIT
This server cannot be deployed
Operate GitHub from your AI assistant: repos, PRs, issues, Actions. Previews and read-only mode.
Access the GitHub API, enabling file operations, repository management, search functionality, and…
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.
