Mkusaka MCP Server Perplexity

🚀 Perplexity AI MCP Server

An MCP server implementation integrating the Perplexity AI API, offering advanced search capabilities and multiple model options.

🚀 Quick Start

The Perplexity AI MCP Server is an innovative solution that integrates the Perplexity AI API, enabling users to perform high - level searches with various model choices.

✨ Features

• Conduct searches using Perplexity AI's models.
• Support all official Sonar models.
• Configurable number of search results.
• Detailed error handling and logging.
• Compatibility with MCP Inspector.

📦 Available Models

• sonar - reasoning - pro (127k context)
• sonar - reasoning (127k context)
• sonar - pro (200k context)
• sonar (127k context)

📦 Installation

pnpm install
pnpm build

📚 Configuration

API Key

1. Sign up for a new account on Perplexity AI Account.
2. Obtain your API key from the dashboard.
3. Set the environment variable:

export PERPLEXITY_API_KEY=your_api_key_here

💻 Usage Examples

Direct Execution

node dist/index.js
# Or if you've made it executable
./dist/index.js

Development

pnpm dev

Testing with MCP Inspector

pnpm inspect

📚 Documentation

perplexity_search

Execute a search using Perplexity AI's models.

Parameters:

• query (string, required): The search query.
• model (string, optional): The model to use (default: "sonar").
  • Available options: sonar - reasoning - pro, sonar - reasoning, sonar - pro, sonar.
• count (number, optional): The number of results (1 - 10, default: 5).

🔧 Technical Details

Project Structure

src/perplexity/
├── index.ts        # Main server implementation file
├── lib/
│   └── logger.ts   # Logging configuration
└── adr.md         # Architectural decision record

Logging

Logs are written to the perplexity - mcp.log file in the project root directory.

📄 License

MIT

🤝 Contribution Guidelines

1. Fork the repository.
2. Create your feature branch.
3. Commit your changes.
4. Push to the branch.
5. Create a new Pull Request.