广告合作
MCP.so
登录

MCP Server for Documentation Search

@deepmihir

代码仓库

基本信息

分类

记忆与知识

许可证

MIT

传输方式

stdio

作者

deepmihir

关于 MCP Server for Documentation Search

暂无概览

#mcp#server#documentation-search

MCP Server for Documentation Search 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "MCP-Server-Tutorial": {
      "command": "uv",
      "args": [
        "init",
        "mcp-server"
      ]
    }
  }
}

MCP Server for Documentation Search 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 MCP Server for Documentation Search?

MCP Server for Documentation Search is a custom MCP (Model Control Protocol) server that enables Claude to search through documentation for popular Python libraries including LangChain, LlamaIndex, and OpenAI. It integrates with the Google Search API via Serper for finding relevant documentation pages and uses web scraping to extract content from those pages.

How to use MCP Server for Documentation Search?

Install Python 3.10+, MCP SDK 1.2.0+, and the uv package manager. Create a new project with uv, install dependencies (mcp[cli] and httpx), create the server implementation file main.py, then run the server with uv run main.py. Connect to Claude Desktop by editing the claude_desktop_config.json file with the appropriate command and arguments pointing to your project directory.

Key features of MCP Server for Documentation Search

  • Search documentation for specific queries across supported Python libraries
  • Google Search API integration via Serper for finding documentation pages
  • Web scraping capabilities to extract content from documentation pages
  • Designed to work with Claude Desktop through the MCP protocol

Use cases of MCP Server for Documentation Search

  • Querying LangChain, LlamaIndex, or OpenAI documentation for specific functions or concepts
  • Obtaining relevant documentation pages and their content for AI assistant responses
  • Enabling Claude to answer programming questions with up-to-date library documentation

常见问题

1

What are the system requirements?

Python 3.10 or higher, MCP SDK 1.2.0 or higher, and the `uv` package manager.

2

Which Python libraries are supported for documentation search?

LangChain, LlamaIndex, and OpenAI.

3

How do I connect the server to Claude Desktop?

Edit the file `~/Library/Application Support/Claude/claude_desktop_config.json` and add the MCP server configuration with the `uv` command, the absolute path to your project directory, and the run command for `main.py`.

4

How does the server find documentation pages?

It uses the Google Search API via Serper to search for relevant documentation pages, then scrapes the content from those pages.

5

What should I do if the server isn't recognized by Claude Desktop?

Check that the configuration file path and permissions are correct, verify the absolute path in the configuration, ensure `uv` is properly installed and accessible, and review Claude Desktop logs for errors.

评论

记忆与知识 分类下的更多 MCP 服务器

Sensefold

SenseFold Labs

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au

Scento Perfume API (MCP server): free fragrance API, no key

Scento

Scento Perfume API is a free fragrance API and perfume notes database for developers and AI agents. Search 1,500+ perfumes and 400+ ingredients, compare scents, find similar perfumes, map scent families and build occasio

Memlord

MyrikLD

Memlord is a remote MCP server available at https://app.memlord.com.

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

66

Codebase Memory

DeusData

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

46.7K
广告合作