Repocrunch MCP Server

@kimwwk

代码仓库主页

基本信息

分类

开发工具

许可证

MIT

传输方式

stdio

作者

kimwwk

提交者

chillkimtest-oss

关于 Repocrunch MCP Server

Deterministic analyzer that turns GitHub repos into structured JSON

#github #code-analysis #developer-tools #repository

Repocrunch MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

Repocrunch MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

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

常见问题

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.

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.

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.

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++.

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`.

开发工具分类下的更多 MCP 服务器

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

UXMachine

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up