@vapi-ai/mcp-docs-server

@vapi-ai/mcp-docs-server

Turn your IDE into a Vapi expert! 🎯

This is a Model Context Protocol (MCP) server that provides comprehensive access to Vapi documentation, examples, and knowledge base. It integrates seamlessly with AI-powered IDEs like Cursor, Windsurf, and VSCode to give you instant access to Vapi expertise.

✨ Features

• 📚 Complete Documentation Access - Search through all Vapi docs
• 💻 Ready-to-Use Examples - Get working code for any Vapi feature
• 🔧 API Reference - Detailed API documentation with examples
• 📖 Step-by-Step Guides - Implementation tutorials
• 📋 Changelog - Latest updates and new features
• 🔍 Smart Search - Semantic search across all content
• 🎯 Context-Aware - Provides relevant information based on your queries

🚀 Quick Start

Installation

npm install -g @vapi-ai/mcp-docs-server

IDE Configuration

The server is automatically configured when you run vapi mcp setup from the Vapi CLI.

Manual Configuration

Cursor IDE

Add to your .cursor/mcp.json:

{
  "mcpServers": {
    "vapi": {
      "command": "vapi-mcp-docs-server",
      "args": []
    }
  }
}

Windsurf IDE

Add to your .codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "vapi": {
      "command": "vapi-mcp-docs-server",
      "args": []
    }
  }
}

VSCode

Add to your .vscode/mcp.json:

{
  "servers": {
    "vapi": {
      "command": "vapi-mcp-docs-server",
      "args": []
    }
  }
}

🛠️ Available Tools

Once configured, your IDE's AI assistant will have access to these tools:

search_documentation

Search Vapi documentation for specific topics, features, or concepts.

Search for "phone calls" → Get comprehensive guides on making calls
Search for "webhooks" → Learn about real-time event handling
Search for "voice settings" → Configure voice providers and parameters

get_examples

Get code examples for specific Vapi features or use cases.

Get examples for "assistants" in TypeScript
Get examples for "function calling" in Python
Get examples for "voice configuration" in all languages

get_guides

Access step-by-step guides for implementing Vapi features.

Get guides for "getting started"
Get guides for "phone calls"
Get guides for "tools and functions"

get_api_reference

Get detailed API reference information for Vapi endpoints.

Get API reference for "assistants"
Get API reference for "calls" with POST method
Get API reference for "webhooks" with examples

get_changelog

Get recent changes, updates, and new features in Vapi.

Get latest 5 changelog entries
Get changelog for version "1.8.0"
Get only "features" type changes

🎯 Example Usage

Once configured, you can ask your IDE's AI assistant questions like:

• "How do I create a voice assistant with Vapi?"
• "Show me examples of making phone calls"
• "What are the latest Vapi features?"
• "How do I set up webhooks for function calling?"
• "Give me the API reference for creating assistants"

The AI will automatically use the MCP tools to provide accurate, up-to-date information!

🔧 Development

Prerequisites

• Node.js 18+
• npm or yarn

Setup

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

# Install dependencies
npm install

# Build the project
npm run build

# Start development server
npm run dev

Testing

# Run tests
npm test

# Lint code
npm run lint

# Fix linting issues
npm run lint:fix

Project Structure

src/
├── index.ts              # Main entry point
├── server.ts             # MCP server implementation
├── tools/                # MCP tools
│   ├── search.ts         # Documentation search
│   ├── examples.ts       # Code examples
│   ├── guides.ts         # Step-by-step guides
│   ├── api-reference.ts  # API documentation
│   └── changelog.ts      # Version history
├── resources/            # MCP resources
│   └── documentation.ts  # Resource handlers
└── utils/                # Utilities
    └── documentation-data.ts # Data and types

📖 How It Works

This MCP server implements the Model Context Protocol to provide structured access to Vapi's knowledge base. When your IDE's AI assistant needs information about Vapi:

• Query Processing - The AI identifies what information is needed
• Tool Selection - Chooses the appropriate MCP tool
• Content Retrieval - Fetches relevant documentation/examples
• Response Generation - Provides accurate, contextual answers

🤝 Contributing

We welcome contributions! Here's how you can help:

• Add Content - Expand documentation, examples, or guides
• Improve Search - Enhance search algorithms and relevance
• Fix Bugs - Report and fix issues
• Add Features - Propose new tools or capabilities

Contributing Guidelines

• Fork the repository
• Create a feature branch (git checkout -b feature/amazing-feature)
• Make your changes
• Add tests if applicable
• Run linting and tests (npm run lint && npm test)
• Commit your changes (git commit -m 'Add amazing feature')
• Push to the branch (git push origin feature/amazing-feature)
• Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔗 Links

• Vapi Website - Voice AI platform
• Vapi Documentation - Complete docs
• Vapi CLI - Command-line tool
• Vapi Discord - Community support
• Model Context Protocol - MCP specification

🆘 Support

• Issues - GitHub Issues
• Discord - Vapi Community
• Email - [e-mail]

Made with ❤️ by the Vapi team