Github Analyzer Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Github Analyzer Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<div align="center">
<p> <img src="https://img.shields.io/badge/MCP-Model%20Context%20Protocol-7c3aed?style=for-the-badge"/> <img src="https://img.shields.io/badge/Claude-Compatible-f97316?style=for-the-badge&logo=anthropic&logoColor=white"/> <img src="https://img.shields.io/badge/PyPI-github--analyzer--mcp-3776AB?style=for-the-badge&logo=pypi&logoColor=white"/> <img src="https://img.shields.io/badge/Python-3.10%2B-3776AB?style=for-the-badge&logo=python&logoColor=white"/> <img src="https://img.shields.io/badge/License-MIT-22C55E?style=for-the-badge"/> </p>
<p> <b>An MCP server that gives Claude 8 powerful GitHub analysis tools — analyze any repo, score its health, find issues, search code, and more — directly inside Claude Desktop.</b> </p>
</div>
Once installed, you can ask Claude things like:
"Analyze the health of the langchain repo" "Who are the top contributors to pytorch/pytorch?" "Find all open bug issues in fastapi" "Search for TODO comments in microsoft/vscode" "What languages does the Next.js repo use?" "Show me recent commits to the main branch of tensorflow"
Claude uses this MCP server to fetch real GitHub data and give you deep, structured analysis.
| Tool | Description |
|---|---|
analyze_repo | Full repo overview — stars, forks, metadata, activity |
get_contributors | Top contributors with commit counts |
find_issues | Open/closed issues with label filtering |
search_code | Find code patterns across a repo |
get_languages | Language breakdown with percentages |
analyze_commits | Recent commit history and author patterns |
get_pull_requests | Open/merged PRs with review metadata |
repo_health_score | 0-100 health score with improvement suggestions |
pip install github-analyzer-mcpgit clone https://github.com/MidhunaMohanraj/github-analyzer-mcp
cd github-analyzer-mcp
pip install -e .Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"github-analyzer": {
"command": "github-analyzer-mcp",
"env": {
"GITHUB_TOKEN": "your_github_token_here"
}
}
}
}Then restart Claude Desktop. You'll see the GitHub tools available in Claude's tool panel.
Without a token: 60 requests/hour limit. With a token: 5,000 requests/hour + access to private repos.
Get a free token at: github.com/settings/tokens → Generate new token (classic) → check public_repo scope.
# Set token (optional)
export GITHUB_TOKEN=your_token_here
# Run the server directly
github-analyzer-mcp
# Or test with MCP inspector
npx @modelcontextprotocol/inspector github-analyzer-mcpRepo health check:
You: "Give me a health score for the huggingface/transformers repo" Claude: Uses `repo_health_score` → Returns 87/100, Grade A, with specific recommendations
Code search:
You: "Search for all uses of 'deprecated' in the requests library" Claude: Uses `search_code` → Returns file locations and code snippets
Contributor analysis:
You: "Who are the top 5 contributors to kubernetes/kubernetes?" Claude: Uses `get_contributors` → Returns ranked list with commit counts
github-analyzer-mcp/
├── src/github_analyzer_mcp/
│ ├── __init__.py
│ └── server.py # 8 MCP tools
├── pyproject.toml # PyPI config
├── README.md
└── LICENSEPRs welcome! Open an issue first to discuss major changes.
MIT — see LICENSE
<div align="center">
⭐ Star this repo if you find it useful!
Built with ❤️ using MCP · Compatible with Claude Desktop
</div>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.