DevDocs MCP Server

DevDocs MCP Server

Provides access to 600+ documentation libraries from DevDocs.io including Python, JavaScript, React, Django, and more. Enables searching, browsing, and retrieving documentation content directly through Claude Desktop.

Category
访问服务器

README

DevDocs MCP Server

A Model Context Protocol (MCP) server that provides access to the extensive DevDocs.io API documentation library. Access 600+ documentation sets including Python, JavaScript, React, Django, PostgreSQL, and many more directly through Claude Desktop or any MCP-compatible client.

Features

  • List Documentation Sets: Browse all 600+ available documentation libraries
  • Search Within Docs: Search for specific topics within a documentation set
  • Global Search: Search across multiple documentation sets simultaneously
  • Fetch Content: Retrieve full HTML documentation content
  • Browse Index: View complete table of contents for any documentation
  • Smart Caching: Automatic caching for improved performance
  • Type Safety: Built with TypeScript for reliability

Available Documentation

DevDocs.io aggregates documentation from numerous sources including:

  • Languages: Python, JavaScript, TypeScript, Rust, Go, C++, Ruby, PHP, Java, Kotlin, Swift, and 30+ more
  • Frameworks: React, Vue, Angular, Django, Flask, Laravel, Rails, Express, Next.js, and many more
  • Libraries: NumPy, pandas, PyTorch, TensorFlow, D3.js, Lodash, jQuery
  • Tools: Docker, Kubernetes, Git, webpack, npm, CMake
  • Databases: PostgreSQL, MySQL, SQLite, Redis, MongoDB
  • Web APIs: DOM, HTML, CSS, HTTP, Web APIs from MDN

Installation

Prerequisites

  • Node.js 18 or higher
  • npm or yarn

Setup

  1. Clone or download this repository:
git clone <repository-url>
cd apidocs
  1. Install dependencies:
npm install
  1. Build the project:
npm run build

Configure Claude Desktop

Add this server to your Claude Desktop configuration file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "devdocs": {
      "command": "node",
      "args": ["/absolute/path/to/apidocs/build/index.js"]
    }
  }
}

Replace /absolute/path/to/apidocs with the actual path to your installation.

Tools

The server provides five powerful tools:

1. list_docs

List all available documentation sets with optional filtering.

Parameters:

  • filter (optional): String to filter documentation by name

Example:

{
  "filter": "python"
}

Returns: Array of documentation metadata including name, slug, version, links, and size.

2. search_doc

Search within a specific documentation set.

Parameters:

  • doc_slug (required): Documentation slug (e.g., "javascript", "python~3.12", "react")
  • query (required): Search query string

Example:

{
  "doc_slug": "javascript",
  "query": "array map"
}

Returns: Array of matching entries with name, path, type, and full URL (limited to 20 results).

3. search_all_docs

Search across multiple documentation sets simultaneously.

Parameters:

  • query (required): Search query string
  • doc_slugs (optional): Array of specific documentation slugs to search

Example:

{
  "query": "authentication",
  "doc_slugs": ["django~5.1", "flask~3.1", "express"]
}

Returns: Combined search results from multiple docs (limited to 50 results).

4. get_doc_content

Fetch the full HTML content for a specific documentation entry.

Parameters:

  • doc_slug (required): Documentation slug
  • path (required): Entry path (from search results)

Example:

{
  "doc_slug": "javascript",
  "path": "global_objects/array/map"
}

Returns: Full HTML content of the documentation entry.

5. get_doc_index

Get the complete index/table of contents for a documentation set.

Parameters:

  • doc_slug (required): Documentation slug

Example:

{
  "doc_slug": "react"
}

Returns: Complete index with entry names, paths, and types (first 100 entries shown).

Usage Examples

Finding Python Documentation

  1. List Python docs:

    • Tool: list_docs
    • Filter: "python"
  2. Search for "list comprehension":

    • Tool: search_doc
    • doc_slug: "python~3.12"
    • query: "list comprehension"
  3. Get the content:

    • Tool: get_doc_content
    • doc_slug: "python~3.12"
    • path: (from search results)

Cross-Framework Search

Search for "routing" across web frameworks:

  • Tool: search_all_docs
  • query: "routing"
  • doc_slugs: ["express", "django~5.1", "flask~3.1", "rails~7.2"]

Development

Watch Mode

For development with auto-rebuild:

npm run watch

Project Structure

apidocs/
├── src/
│   └── index.ts         # Main MCP server implementation
├── build/               # Compiled JavaScript (generated)
├── package.json         # Dependencies and scripts
├── tsconfig.json        # TypeScript configuration
└── README.md           # This file

How It Works

  1. Data Source: Fetches data from DevDocs.io public endpoints
  2. Caching: Implements 1-hour cache to reduce API calls and improve performance
  3. Index Format: DevDocs uses compact arrays [name, path, type] for efficient storage
  4. Content Delivery: HTML partials are served for each documentation entry

API Endpoints Used

  • https://devdocs.io/docs.json - List of all documentation sets
  • https://documents.devdocs.io/{slug}/index.json - Index for specific documentation
  • https://documents.devdocs.io/{slug}/{path}.html - Content for specific entry

Troubleshooting

Server Not Showing Up in Claude Desktop

  1. Verify the path in claude_desktop_config.json is absolute
  2. Ensure you ran npm run build
  3. Restart Claude Desktop completely
  4. Check Claude Desktop logs for errors

Search Returns No Results

  • Verify the doc_slug is correct using list_docs
  • Check that the documentation includes the term you're searching for
  • Try a broader search query

Performance Issues

  • The server caches all requests for 1 hour
  • First requests may be slower as data is fetched
  • Subsequent requests will be much faster

Credits and Attribution

This MCP server was built by analyzing and integrating with the DevDocs.io platform. Special thanks to:

Core Infrastructure

Documentation and Research

Technology Stack

All documentation content is copyright of their respective owners and provided through DevDocs.io's public API.

For detailed attribution, see CREDITS.md.

License

MIT - See LICENSE for details.

Contributing

Contributions are welcome! Please feel free to submit issues or pull requests.

Resources

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选