Documentation Retrieval MCP Server (DOCRET)

@Sreedeep-SS

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

ライセンス

MIT

トランスポート

stdio

作者

Sreedeep-SS

Documentation Retrieval MCP Server について

A Model Context Protocol (MCP) server

#docret#mcp-server#documentation-retrieval

Documentation Retrieval 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": {
    "docret-mcp-server": {
      "command": "python",
      "args": [
        "main.py"
      ]
    }
  }
}

Documentation Retrieval 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 Documentation Retrieval MCP Server (DOCRET)?

Documentation Retrieval MCP Server (DOCRET) is a Model Context Protocol (MCP) server that enables AI assistants to access up-to-date documentation for Python libraries such as LangChain, LlamaIndex, and OpenAI. It dynamically fetches and provides relevant information from official documentation sources, ensuring AI applications always have access to the latest content.

How to use Documentation Retrieval MCP Server (DOCRET)?

Clone the repository, create and activate a virtual environment, install dependencies with pip install -r requirements.txt (or uv sync), set the SERPER_API_KEY environment variable in a .env file, and run python main.py. The server exposes a get_docs function that takes a query and library parameter. Integrate with AI assistants by adding a JSON configuration to the assistant’s MCP server list.

Key features of Documentation Retrieval MCP Server (DOCRET)

Dynamic retrieval of documentation content for Python libraries.
Asynchronous web searches using the SERPER API.
HTML parsing with BeautifulSoup to extract readable text.
Extensible design: easily add new libraries by updating the docs_urls dictionary.
Currently supports LangChain, LlamaIndex, and OpenAI.

Use cases of Documentation Retrieval MCP Server (DOCRET)

AI assistants answering user questions about Python library APIs and usage.
Keeping AI applications updated with the latest official documentation.
Providing context for code generation or debugging sessions.
Integrating with Claude Desktop or Claude Code for real-time documentation lookup.

よくある質問

What is the Model Context Protocol?

The Model Context Protocol is an open standard that enables secure, two-way connections between data sources and AI-powered tools. Developers can expose data through MCP servers or build AI applications (MCP clients) that connect to these servers.

What are the prerequisites for using this server?

You need Python 3.8 or higher, a package manager (UV or pip), a Serper API key, and Claude Desktop or Claude Code for testing.

Which Python libraries are currently supported?

The server currently supports LangChain, LlamaIndex, and OpenAI.

How can I add support for an additional library?

Add the library name and its documentation URL to the `docs_urls` dictionary in `main.py`. The server will then be able to search and retrieve documentation from that URL.

How do I run the MCP server after installation?

After setting up the environment and API key, run `python main.py` from the project root directory to launch the server.

「メモリとナレッジ」の他のコンテンツ

priostack

ideaswave

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths