Back to MCP Catalog

Perplexity MCP Server

SearchPython
Access Perplexity's AI search capabilities with citations through MCP
Available Tools

ask_perplexity

Request chat completion with citations from Perplexity

Perplexity MCP Server provides a seamless integration with Perplexity's powerful AI search API, allowing you to perform web searches with AI-generated answers and citations directly from your MCP-compatible client. This server bridges the gap between your AI assistant and Perplexity's knowledge retrieval capabilities, enabling more accurate and up-to-date responses with proper attribution. Note that there are currently some limitations with long-running operations in certain clients like Claude Desktop, which may timeout if Perplexity processing takes too long. Future updates will address these limitations as client support for long-running operations improves.

Overview

The Perplexity MCP Server allows you to harness Perplexity's AI search capabilities directly from your MCP-compatible client. This integration enables your AI assistant to perform web searches and provide answers with proper citations, enhancing the accuracy and reliability of responses.

Prerequisites

Before installing the Perplexity MCP Server, you'll need:

  1. A Perplexity API key (obtain one from Perplexity's website)
  2. An MCP-compatible client (such as Claude Desktop)
  3. Python installed on your system

Installation

Using pip/uv

The simplest way to install the Perplexity MCP Server is using pip or uv:

pip install mcp-server-perplexity
# or
uv install mcp-server-perplexity

Configuration in Claude Desktop

To configure the Perplexity MCP Server in Claude Desktop:

  1. Locate your Claude Desktop configuration file:

    • On macOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
    • On Windows: %APPDATA%/Claude/claude_desktop_config.json
  2. Add the Perplexity MCP Server configuration to the mcpServers section:

"mcpServers": {
  "Perplexity": {
    "command": "uvx",
    "args": [
      "mcp-server-perplexity"
    ],
    "env": {
      "PERPLEXITY_API_KEY": "your-perplexity-api-key"
    }
  }
}

Replace your-perplexity-api-key with your actual Perplexity API key.

Usage

Once installed and configured, you can use the Perplexity MCP Server by asking your AI assistant to search for information using Perplexity. The assistant will use the ask_perplexity tool to query Perplexity's API and return results with citations.

Example prompt: "Can you search Perplexity for the latest information about quantum computing advancements?"

Limitations

  • The Claude Desktop client may timeout if Perplexity processing takes too long
  • This issue might be resolved when Claude Desktop implements support for long-running operations and progress reporting
  • Implementation updates to handle these features will be made if they become available in the future

Troubleshooting

If you encounter issues with the Perplexity MCP Server:

  1. Verify your API key is correct and has sufficient permissions
  2. Check that the server is properly configured in your client's configuration file
  3. Ensure you have the latest version of the MCP server installed

For more detailed information or to report issues, visit the GitHub repository.

Related MCPs

SearXNG
SearchTypeScript

Web search capabilities through SearXNG API integration

Hacker News
SearchPython

Access and search Hacker News content programmatically

Web Search
SearchJavaScript

Free Google search integration with no API keys required

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.