MCP.so
ログイン

Repocrunch MCP Server

@kimwwk

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

トランスポート

stdio

作者

kimwwk

投稿者

chillkimtest-oss

Repocrunch MCP Server について

Deterministic analyzer that turns GitHub repos into structured JSON

Repocrunch MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "repocrunch": {
      "command": "repocrunch",
      "args": [
        "mcp"
      ]
    }
  }
}

Repocrunch MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Repocrunch?

Repocrunch analyzes any public GitHub repository into structured JSON. It returns tech stack, dependencies, architecture, health metrics, and security signals in clean, consistent JSON — with no AI or LLMs, fully deterministic. It can be used as a Python library, CLI tool, REST API, or MCP server, and is aimed at developers who need repository data programmatically.

How to use Repocrunch?

Install via pip: pip install repocrunch (requires Python 3.11+). Then use the CLI: repocrunch analyze owner/repo --pretty or start the MCP server with repocrunch mcp. Optionally set a GitHub token via export GITHUB_TOKEN=... for higher rate limits and private repo access. Use the Python library with from repocrunch import analyze or the REST API by running repocrunch serve.

Key features of Repocrunch

  • Analyzes any public GitHub repository into structured JSON
  • Detects tech stack, dependencies, architecture, health, and security
  • Provides a CLI, Python library, REST API, and MCP server
  • Fully deterministic — no AI or LLM involved
  • Supports 40+ frameworks across multiple ecosystems
  • Optional GitHub token raises API limit to 5,000 calls/hour

Use cases of Repocrunch

  • Quickly inspect a repository’s tech stack and dependencies before contributing
  • Audit repository health and security signals for open-source dependency decisions
  • Automate repository metadata extraction in CI/CD pipelines or internal tools
  • Integrate repository analysis into AI assistants via the MCP server (Claude, Cursor)
  • Compare multiple repositories programmatically using the Python library or CLI

よくある質問

1

What runtime does Repocrunch require?

Repocrunch requires Python 3.11 or higher. It can be installed via pip or uv, and runs on any platform that supports Python.

2

Does Repocrunch use AI or LLMs?

No. Repocrunch is fully deterministic and does not rely on any AI or large language models. It analyzes repository structure and metadata algorithmically.

3

How does Repocrunch access repository data?

It uses the GitHub API to fetch repository information. By default, without a GitHub token, you get 60 API calls per hour. Setting a token raises the limit to 5,000 per hour and also allows analysis of private repositories you have access to.

4

What data does Repocrunch detect?

It detects summary (stars, forks, license), tech stack (runtime, framework, package manager, dependencies), architecture (monorepo, Docker, CI/CD), health (commit frequency, contributors, issues), and security signals (env file, Dependabot, branch protection, security policy). Supported ecosystems include JavaScript/TypeScript, Python, Rust, Go, Java/Kotlin, Ruby, and C/C++.

5

How do I run Repocrunch as an MCP server?

Run `repocrunch mcp` to start the MCP server over STDIO transport. This allows integration with MCP clients such as Claude Desktop and Cursor. For REST API, use `repocrunch serve` and access endpoints like `/analyze?repo=owner/repo`.

コメント

「開発者ツール」の他のコンテンツ