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.
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 documentationversion(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
- 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"
}
}
}
}
- Restart Claude Desktop
Claude Code Installation
For Claude Code, you can use the built-in MCP configuration:
- Via Smithery CLI (Recommended):
npx -y @smithery/cli install expo-docs-mcp --client claude-code
- 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
- 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 documentationv53: Expo SDK 53v52: Expo SDK 52v51: 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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.