mcp-perplexity

mcp-perplexity

3.2

If you are the rightful owner of mcp-perplexity and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Perplexity MCP Server provides a Python-based interface to the Perplexity API, offering tools for querying responses, maintaining chat history, and managing conversations.

The Perplexity MCP Server is designed to mimic user interactions with the Perplexity Chat on a browser, allowing models to ask questions, continue conversations, and list all chats. Built with Python and setuptools, it supports model configuration via environment variables and stores chat data locally. The server is integrated with development environments and provides a web interface for easier interaction and management of chats. It includes tools for expert programming assistance, ongoing conversations, chat listing, and chat history retrieval. The server is compatible with Python 3.10 or higher and requires the uvx package manager.

Features

  • Model Configuration via Environment Variable: Allows you to specify the Perplexity model using the PERPLEXITY_MODEL environment variable for flexible model selection.
  • Persistent Chat History: The chat_perplexity tool maintains ongoing conversations with Perplexity AI, creating new chats or continuing existing ones with full history context.
  • Streaming Responses with Progress Reporting: Uses progress reporting to prevent timeouts on slow responses.

Tools

  1. ask_perplexity

    Request expert programming assistance through Perplexity, focusing on coding solutions, error debugging, and technical explanations.

  2. chat_perplexity

    Maintains ongoing conversations with Perplexity AI, creating new chats or continuing existing ones with full history context.

  3. list_chats_perplexity

    Lists all available chat conversations with Perplexity AI, returning chat IDs, titles, and creation dates.

  4. read_chat_perplexity

    Retrieves the complete conversation history for a specific chat from local storage.