Laodev1 Perplexity MCP Server

🚀 Perplexity MCP Server

The Perplexity MCP Server is an Anthropic's Model Context Protocol (MCP) server implemented in Node.js, enabling Claude to interact with Perplexity's language models. This server provides a secure bridge between the capabilities of Claude and Perplexity AI, facilitating enhanced AI interactions through tool usage.

🚀 Quick Start

Prerequisites

• Node.js installed on your system.
• A valid Perplexity API key.

Installation

1. Clone the repository:

git clone https://github.com/yourusername/perplexity-mcp-server.git
cd perplexity-mcp-server

2. Install dependencies:

npm install

3. Create a .env file:

PERPLEXITY_API_KEY=your-api-key-here

4. Build the project:

npm run build

Configuration in Claude Desktop

To add this server to Claude Desktop, update your claude_desktop_config.json:

{
  "mcpServers": {
    //more servers...
    "perplexity": {
      "command": "node",
      "args": ["path\\to\\perplexity-mcp-server\\dist\\index.js"],
      "env": {
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY"
      }
    }
    //more servers...
  }
}

The configuration file is typically located at:

• Windows: %APPDATA%/Claude/config/claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/config/claude_desktop_config.json
• Linux: ~/.config/Claude/config/claude_desktop_config.json

Start Development Server

Start the development server with automatic recompilation:

npm run dev

✨ Features

Available Tools

The current server implements two main tools:

1. perplexity_chat

An advanced chat completion tool with full message history support.

{
  "name": "perplexity_chat",
  "description": "Generate chat completions from Perplexity AI",
  "parameters": {
    "model": "string (optional) - One of: llama-3.1-sonar-small-128k-online, llama-3.1-sonar-large-128k-online, llama-3.1-sonar-huge-128k-online",
    "messages": "array of {role, content} objects - Conversation history",
    "temperature": "number (optional) - Sampling temperature, between 0 - 2"
  }
}

2. perplexity_ask

A simplified single-query interface for quick questions.

{
  "name": "perplexity_ask",
  "description": "Send a simple query to Perplexity AI",
  "parameters": {
    "query": "string - The question or prompt to send",
    "model": "string (optional) - One of: llama-3.1-sonar-small-128k-online, llama-3.1-sonar-large-128k-online, llama-3.1-sonar-huge-128k-online"
  }
}

💻 Usage Examples

Creating a Server

const { PerplexityServer } = require('@modelcontextprotocol/sdk');

const server = new PerplexityServer({
  port: 3000,
  apiKey: 'your-api-key-here'
});

server.start();

Sending a Query

{
  "name": "perplexity_ask",
  "description": "Send a simple query to Perplexity AI",
  "parameters": {
    "query": "string - The question or prompt to send",
    "model": "string (optional) - One of: llama-3.1-sonar-small-128k-online, llama-3.1-sonar-large-128k-online, llama-3.1-sonar-huge-128k-online"
  }
}

📚 Documentation

Core Components

1. PerplexityServer Class

• Implements the MCP server protocol.
• Handles tool registration and execution.
• Manages error handling and server lifecycle.

2. Tools System

• Modular tool definitions.
• Type-safe tool handlers.
• Structured input validation.

Technical Details

• Implements type safety using TypeScript.
• Implements the MCP protocol through @modelcontextprotocol/sdk.
• Communicates via stdio transport.
• Manages configuration through environment variables.

Error Handling

The server implements comprehensive error handling:

• API error reporting.
• Handling of invalid tool requests.
• Management of connection errors.
• Handling of process signals.

Dependencies

• @modelcontextprotocol/sdk
• node

npm install @modelcontextprotocol/sdk node

🔧 Technical Details

• Type safety is achieved using TypeScript.
• The MCP protocol is implemented via @modelcontextprotocol/sdk.
• Communication is done through stdio transport.
• Configuration is managed using environment variables.

📄 License

No license information provided in the original document.