広告掲載
MCP.so
ログイン
G

Gossiphs MCP Server

@williamfzc

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

williamfzc

投稿者

williamfzc

Gossiphs MCP Server について

"Zero setup" & "Blazingly fast" general code file relationship analysis. With Python & Rust. Based on tree-sitter and git analysis. Support MCP and ready for AI🤖

#python#code-navigation#codebase

Gossiphs 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": {
    "gossiphs": {
      "url": "http://127.0.0.1:8000/sse"
    },
    "gossiph-cmd": {
      "command": "gossiphs-mcp",
      "args": [
        "server"
      ]
    }
  }
}

Gossiphs 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。

上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。

概要

What is Gossiphs?

Gossiphs is a "zero setup" and "blazingly fast" code file relationship analysis tool that uses tree-sitter and git history to build a graph of symbol definitions and references across files. It is designed for developers and AI integration, providing a Python SDK and support for the Model Context Protocol (MCP).

How to use Gossiphs?

Install via pip install gossiphs, then use the Python API to configure a project path and create a NetworkX graph of file relationships. Alternatively, use the CLI to export CSV files or start an HTTP service. For MCP integration, see the dedicated MCP README.

Key features of Gossiphs

  • Zero repository-specific configuration required.
  • Blazingly fast analysis using tree-sitter and git analysis.
  • Supports multiple languages (Rust, Python, TypeScript, JavaScript, Golang, Java, Kotlin, Swift).
  • Can export relationship graphs as CSV or serve via HTTP.
  • MCP support for seamless AI integration.
  • Acceptable accuracy (88–94% coverage of LSP edges in tested repos).

Use cases of Gossiphs

  • Guiding context during IDE development.
  • Facilitating code browsing on websites.
  • Impact analysis of code changes in CI systems.
  • Querying references and definitions across a codebase for complex analysis.

よくある質問

1

What is the main advantage over stack-graphs or LSP?

Gossiphs trades high precision for zero configuration and broad language support, using commit histories to refine edges instead of complex scope analysis. It offers acceptable accuracy with lower setup cost.

2

Which languages are currently supported?

Supported languages: Rust, Python, TypeScript, JavaScript, Golang, Java, Kotlin, and Swift. Rules for additional languages can be added via tree-sitter queries.

3

How does it achieve zero setup?

Gossiphs does not require per-repository configuration; it automatically extracts imports/exports and uses commit history to infer relationships between files.

4

Where does the data live?

Analysis runs locally – the graph is built in memory and can be exported to CSV or used via HTTP service. No remote storage is mentioned.

5

What are the known limitations?

Static analysis cannot handle dynamic binding, so it may miss some references that LSP would find. Precision is lower than LSP but sufficient for many use cases.

コメント

「その他」の他のコンテンツ

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
広告掲載