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.
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
- Clone or download this repository:
git clone <repository-url>
cd apidocs
- Install dependencies:
npm install
- 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 stringdoc_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 slugpath(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
-
List Python docs:
- Tool:
list_docs - Filter:
"python"
- Tool:
-
Search for "list comprehension":
- Tool:
search_doc - doc_slug:
"python~3.12" - query:
"list comprehension"
- Tool:
-
Get the content:
- Tool:
get_doc_content - doc_slug:
"python~3.12" - path: (from search results)
- Tool:
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
- Data Source: Fetches data from DevDocs.io public endpoints
- Caching: Implements 1-hour cache to reduce API calls and improve performance
- Index Format: DevDocs uses compact arrays
[name, path, type]for efficient storage - Content Delivery: HTML partials are served for each documentation entry
API Endpoints Used
https://devdocs.io/docs.json- List of all documentation setshttps://documents.devdocs.io/{slug}/index.json- Index for specific documentationhttps://documents.devdocs.io/{slug}/{path}.html- Content for specific entry
Troubleshooting
Server Not Showing Up in Claude Desktop
- Verify the path in
claude_desktop_config.jsonis absolute - Ensure you ran
npm run build - Restart Claude Desktop completely
- 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
- DevDocs.io - The amazing documentation aggregation platform that makes this possible
- freeCodeCamp - Maintainers of the DevDocs open-source project
- Model Context Protocol SDK - Framework for building MCP servers
Documentation and Research
- documents.devdocs.io - API endpoint for accessing documentation content
- SitePoint - Analysis and overview of DevDocs architecture
- GitHub Docs - API documentation and best practices
Technology Stack
- TypeScript - Type-safe development
- Node.js - Runtime environment
- node-fetch - HTTP client library
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
- DevDocs.io - Main documentation site
- DevDocs GitHub - Source code
- MCP Documentation - Learn about MCP
- Claude Desktop - Download Claude Desktop
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。