MCP HubMCP Hub
spences10

mcp-perplexity-search

by: spences10

🔎 A Model Context Protocol (MCP) server for integrating Perplexity's AI API with LLMs.

8created 22/01/2025
Visit
AI
LLM

📌Overview

Purpose: To integrate Perplexity's AI API with large language models (LLMs) by providing advanced chat completion capabilities.

Overview: The MCP Perplexity Search server enhances chat interactions by leveraging specialized prompt templates suited for a variety of use cases, facilitating effective communication and information delivery through AI-driven responses.

Key Features:

  • Advanced Chat Completion: Utilizes Perplexity's AI models for generating detailed and relevant chat responses, catering to various contexts.

  • Predefined Prompt Templates: Offers templates designed for common scenarios such as technical documentation generation, security best practices analysis, code review, and structured API documentation, streamlining use in specialized fields.

  • Custom Template Support: Enables users to create and utilize bespoke prompt templates tailored to unique requirements, enhancing flexibility in communication.

  • Multiple Output Formats: Supports a variety of response formats (text, markdown, JSON), allowing users to choose the most suitable presentation of information.

  • Source URL Inclusion: Provides an option to include source URLs in responses for better context and verification of information.

  • Configurable Model Parameters: Allows fine-tuning of model behavior with adjustable parameters like temperature and max tokens, accommodating diverse output needs.

  • Model Variety Support: Compatible with several Perplexity models, including Sonar and LLaMA, expanding its capabilities across different AI frameworks.

mcp-perplexity-search

⚠️ Notice

This repository is no longer maintained.

The functionality of this tool is now available in mcp-omnisearch, which combines multiple MCP tools in one unified package.

Please use mcp-omnisearch instead.

A Model Context Protocol (MCP) server for integrating Perplexity's AI API with LLMs. This server provides advanced chat completion capabilities with specialized prompt templates for various use cases.

Features

  • 🤖 Advanced chat completion using Perplexity's AI models
  • 📝 Predefined prompt templates for common scenarios:
    • Technical documentation generation
    • Security best practices analysis
    • Code review and improvements
    • API documentation in structured format
  • 🎯 Custom template support for specialized use cases
  • 📊 Multiple output formats (text, markdown, JSON)
  • 🔍 Optional source URL inclusion in responses
  • ⚙️ Configurable model parameters (temperature, max tokens)
  • 🚀 Support for various Perplexity models including Sonar and LLaMA

Configuration

This server requires configuration through your MCP client. Examples for different environments:

Cline Configuration

Add this to your Cline MCP settings:

{
  "mcpServers": {
    "mcp-perplexity-search": {
      "command": "npx",
      "args": ["-y", "mcp-perplexity-search"],
      "env": {
        "PERPLEXITY_API_KEY": "your-perplexity-api-key"
      }
    }
  }
}

Claude Desktop with WSL Configuration

For WSL environments, add this to your Claude Desktop configuration:

{
  "mcpServers": {
    "mcp-perplexity-search": {
      "command": "wsl.exe",
      "args": [
        "bash",
        "-c",
        "source ~/.nvm/nvm.sh && PERPLEXITY_API_KEY=your-perplexity-api-key /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-perplexity-search"
      ]
    }
  }
}

Environment Variables

The server requires the following environment variable:

  • PERPLEXITY_API_KEY: Your Perplexity API key (required)

API

The server implements a single MCP tool with configurable parameters:

chat_completion

Generate chat completions using the Perplexity API with support for specialized prompt templates.

Parameters:

  • messages (array, required): Array of message objects with:
    • role (string): 'system', 'user', or 'assistant'
    • content (string): The message content
  • prompt_template (string, optional): Predefined template to use:
    • technical_docs: Technical documentation with code examples
    • security_practices: Security implementation guidelines
    • code_review: Code analysis and improvements
    • api_docs: API documentation in JSON format
  • custom_template (object, optional): Custom prompt template with:
    • system (string): System message for assistant behaviour
    • format (string): Output format preference
    • include_sources (boolean): Whether to include sources
  • format (string, optional): 'text', 'markdown', or 'json' (default: 'text')
  • include_sources (boolean, optional): Include source URLs (default: false)
  • model (string, optional): Perplexity model to use (default: 'sonar')
  • temperature (number, optional): Output randomness (0-1, default: 0.7)
  • max_tokens (number, optional): Maximum response length (default: 1024)

Development

Setup

  1. Clone the repository
  2. Install dependencies:
pnpm install
  1. Build the project:
pnpm build
  1. Run in development mode:
pnpm dev

Publishing

The project uses changesets for version management. To publish:

  1. Create a changeset:
pnpm changeset
  1. Version the package:
pnpm changeset version
  1. Publish to npm:
pnpm release

Contributing

Contributions are welcome! Feel free to submit a Pull Request.

License

MIT License - see the LICENSE file for details.

Acknowledgments

  • Built on the Model Context Protocol
  • Powered by Perplexity SONAR API