Perplexity MCP Server D34

🚀 Perplexity MCP Server

The Perplexity MCP Server is a Node.js-based implementation of Anthropic's Model Context Protocol (MCP), enabling Claude to interact with Perplexity's language models.

🚀 Quick Start

The Perplexity MCP Server is a server that implements Anthropic's Model Context Protocol (MCP) based on Node.js. It allows Claude to interact with Perplexity's language models. This server provides a secure bridge between the capabilities of Claude and Perplexity AI, enhancing AI interactions through tool usage.

✨ 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": "Use Perplexity AI to generate chat completions",
  "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"
  }
}

📦 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

📚 Documentation

Claude Desktop Configuration

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\\main.js"],
      "env": {
        "NODE_ENV": "production"
      }
    }
  }
}

Replace yourusername with your actual repository owner and ensure Node.js is in the PATH.

Architecture

Core Components

• MCP Protocol Adapter: Implements communication with Claude.
• Tool Execution: Handles calls to the perplexity_chat and perplexity_ask tools.
• API Key Management: Securely uses the Perplexity API key.

Implementation Details

• Organize code using the Node.js module system.
• Use async/await to handle asynchronous operations.
• Implement configuration management through the .env file.

Troubleshooting

Server Startup Issues

• Ensure Node.js is correctly installed.
• Check if package.json and dependencies are complete.

API Access Errors

• Confirm that the API key is correct and valid.
• Check network connections and firewall settings.

Tool Execution Failures

• Verify that input parameters meet the requirements.
• Check the detailed error information in the console output.

💻 Usage Examples

Basic Usage

const express = require('express');
const { Configuration, OpenAIApi } = require('openai');

const app = express();

app.use(express.json());

const configuration = new Configuration({
  apiKey: process.env.PERPLEXITY_API_KEY,
});

const perplexity = new OpenAIApi(configuration);

app.post('/chat', async (req, res) => {
  try {
    const { model, messages, temperature } = req.body;
    
    const completion = await perplexity.chat.completions.create({
      model: model || 'llama-3.1-sonar-small-128k-online',
      messages: messages,
      temperature: temperature || 0.7,
    });

    res.json({ 
      content: completion.choices[0].message.content,
      status: "success"
    });
    
  } catch (error) {
    console.error('Error:', error);
    res.status(500).json({ 
      content: error.message,
      status: "error"
    });
  }
});

app.listen(3000, () => {
  console.log('Server is running at http://localhost:3000');
});

📄 License

The project is released under the MIT License. For detailed information, please refer to the LICENSE file.

👥 Contributors

• Zhang San - Initial implementation
• Li Si - Code optimization

🔗 Links

• Perplexity Official Website
• OpenAI Official Documentation