Expo Docs MCP Server

Expo Docs MCP Server

Enables AI-powered semantic search through Expo SDK documentation across multiple versions (v51-v53 and latest), allowing developers to quickly find relevant documentation with configurable similarity scoring.

Category
访问服务器

README

Expo Docs MCP Server

MCP server for semantic search of pre-indexed Expo documentation. Search through Expo SDK documentation using AI-powered semantic search with version-specific results.

Features

  • 🔍 Semantic Search: AI-powered search through Expo documentation
  • 📚 Version-Specific: Search across different Expo SDK versions (v51, v52, v53, latest)
  • Fast Results: Pre-indexed documentation with HNSW vector search
  • 🎯 Relevant Results: Similarity scoring and configurable result limits

Tools

search-expo-docs

Search Expo documentation using semantic search.

Parameters:

  • query (string, required): The search query to find relevant Expo documentation
  • version (string, required): Expo SDK version (v53, v52, v51, or latest)
  • maxResults (number, optional): Maximum number of results to return (1-10, default: 5)
  • scoreThreshold (number, optional): Minimum similarity score threshold (0.0-1.0, default: 0.0)

Example:

{
  "name": "search-expo-docs",
  "arguments": {
    "query": "how to use camera in expo",
    "version": "v53",
    "maxResults": 3
  }
}

Installation

Via Smithery (Recommended)

Install directly using the Smithery CLI:

npx -y @smithery/cli install expo-docs-mcp --client claude

Manual Installation for Claude Desktop

  1. Add to your Claude Desktop configuration file:

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

{
  "mcpServers": {
    "expo-docs": {
      "command": "npx",
      "args": ["-y", "expo-docs-mcp"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key_here"
      }
    }
  }
}
  1. Restart Claude Desktop

Claude Code Installation

For Claude Code, you can use the built-in MCP configuration:

  1. Via Smithery CLI (Recommended):
npx -y @smithery/cli install expo-docs-mcp --client claude-code
  1. Manual Configuration:
# Add the MCP server to Claude Code
claude mcp add expo-docs npx -y expo-docs-mcp

# Set the OpenAI API key
claude mcp config set expo-docs OPENAI_API_KEY=your_openai_api_key_here

# Verify the configuration
claude mcp list
  1. Alternative Local Build Method:
# Clone and build locally
git clone https://github.com/jaksm/expo-docs-mcp.git
cd expo-docs-mcp
npm install
npm run build

# Add to Claude Code
claude mcp add expo-docs node ./dist/mcp-server.js
claude mcp config set expo-docs OPENAI_API_KEY=your_openai_api_key_here

Environment Variables

  • OPENAI_API_KEY: Required for generating text embeddings during search queries. The server uses OpenAI's text-embedding-3-large model to convert your search queries into vectors that can be matched against the pre-indexed Expo documentation vectors.

Development

# Clone the repository
git clone https://github.com/jaksm/expo-docs-mcp.git
cd expo-docs-mcp

# Install dependencies
npm install

# Build the project
npm run build

# Test the MCP server connection
npm run test:mcp

# Run the server
npm start

# Development mode
npm run dev:server

Available Versions

  • latest: Most recent Expo SDK documentation
  • v53: Expo SDK 53
  • v52: Expo SDK 52
  • v51: Expo SDK 51

Usage Examples

In Claude Desktop or Claude Code

Once installed, you can ask questions about Expo documentation directly:

Camera-related queries:

How do I request camera permissions in Expo v53?

Navigation setup:

Show me how to set up React Navigation with Expo Router in the latest version

Build configuration:

What are the EAS build configuration options for iOS in Expo v52?

SDK-specific features:

What are the new features in Expo SDK 53?

Direct Tool Usage

If calling the tool directly, use this format:

{
  "name": "search-expo-docs",
  "arguments": {
    "query": "camera permissions and usage",
    "version": "v53",
    "maxResults": 3,
    "scoreThreshold": 0.1
  }
}

Architecture

  • Semantic Search: Uses OpenAI embeddings with HNSW indexing
  • Version Management: Separate indexes for each Expo SDK version
  • Pre-processed Data: Documentation is pre-indexed for fast retrieval
  • MCP Protocol: Standard Model Context Protocol implementation

License

MIT

Contributing

Contributions welcome! Please read the contributing guidelines and submit pull requests to the main branch.

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