perplexity-mcp-zerver
The Perplexity MCP Zerver is a server implementation that provides AI-powered research capabilities by interfacing with the Perplexity website, eliminating the need for an API key. It includes features like web search, documentation retrieval, and persistent chat history management using Puppeteer for browser automation.
Perplexity MCP Zerver
A research level Model Context Protocol (MCP) server implementation providing AI-powered research capabilities by interacting with the Perplexity website without requiring an API key.
Features
- Web search integration via Perplexity's web interface.
- Persistent chat history for conversational context.
- Tools for documentation retrieval, API finding, and code analysis.
- TypeScript-first implementation.
- Uses Puppeteer for browser automation.
Tools
- Search on Perplexity.ai.
- Get Documentation with examples.
- Find and evaluate APIs.
- Check deprecated code for specific contexts.
- Extract main article text from URLs and GitHub repositories.
- Maintain ongoing conversations with Perplexity AI.
Installation
- Clone the repository.
- Install dependencies.
- Build the server.
Configuration
Add the server to your MCP configuration file, and replace paths as needed. Restart your IDE or desktop app for changes.
Usage
- Ensure correct configuration in your MCP settings.
- Restart IDE or Claude Desktop.
- Ask the connected AI assistant to use the tools.
Credits
Thanks to DaInfernalCoder.
License
Licensed under the GNU General Public License v3.0.
Disclaimer
For educational and research purposes only. Use responsibly.