Perplexity Insight MCP server

Integrates with Perplexity AI to enable real-time question answering and web search capabilities through customizable tools for direct questions and web queries across multiple Perplexity models.
Back to servers
Setup instructions
Provider
Theo Lawrence
Release date
Mar 16, 2025
Language
TypeScript

This MCP server implementation connects with the Perplexity AI API, providing advanced question answering capabilities through the standardized Model Context Protocol. It enables seamless access to Perplexity's powerful models for AI-assisted research and information retrieval.

Installation and Setup

Requirements

  • Node.js 18+
  • Perplexity API key

Installation Steps

  1. Install dependencies:
npm install
  1. Create a .env file in the root directory with your Perplexity API key:
PERPLEXITY_API_KEY=your_api_key_here
  1. Start the server:
npm start

Using the MCP Server

The server exposes two main tools for interacting with Perplexity AI:

Available Tools

  • perplexity_ask: Send direct questions to Perplexity AI
  • perplexity_search: Perform search queries with Perplexity AI

Supported Models

You can specify which Perplexity model to use:

  • sonar-reasoning (default): Best for general questions
  • sonar-pro: Enhanced capabilities for professional use cases
  • sonar-deep-research: Specialized for complex research queries

Example Queries

To ask a question using a specific model:

Ask Perplexity using sonar-deep-research: What are the latest advancements in quantum computing?

To customize the system prompt and token count:

Search with Perplexity using sonar-pro with system prompt "You are a helpful research assistant" and max tokens 2000: Latest developments in renewable energy

Response Format

Responses follow the MCP specification:

{
  content: [
    {
      type: "text",
      text: "Response content from Perplexity AI"
    }
  ],
  isError: false // or true if an error occurred
}

Windsurf IDE Integration

Configuration Steps

  1. Build the server:
npm run build
  1. In Windsurf, navigate to Settings and find the "AI Settings" or "Model Context Protocol" section

  2. Add a new MCP server with these details:

    • Name: Perplexity Insight
    • Type: Local Process
    • Command: Path to your Node.js executable
    • Arguments: Path to your compiled index.js file
    • Working Directory: Path to your project directory
    • Environment Variables: Include PERPLEXITY_API_KEY=your_api_key_here

Example Configuration JSON

For your mcp_config.json file:

"perplexity-ask": {
  "command": "node",
  "args": [
    "/path/to/perplexity-insight-MCP/dist/index.js"
  ],
  "cwd": "/path/to/perplexity-insight-MCP",
  "env": {
    "PERPLEXITY_API_KEY": "pplx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
  }
}

Troubleshooting

If you encounter issues:

  • Check that your API key is valid and properly set in the .env file
  • Verify that the server is running correctly
  • Look for error messages in the server logs
  • Ensure Windsurf is properly configured to use the MCP server

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "perplexity-ask" '{"command":"node","args":["/path/to/perplexity-insight-MCP/dist/index.js"],"cwd":"/path/to/perplexity-insight-MCP","env":{"PERPLEXITY_API_KEY":"pplx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "perplexity-ask": {
            "command": "node",
            "args": [
                "/path/to/perplexity-insight-MCP/dist/index.js"
            ],
            "cwd": "/path/to/perplexity-insight-MCP",
            "env": {
                "PERPLEXITY_API_KEY": "pplx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "perplexity-ask": {
            "command": "node",
            "args": [
                "/path/to/perplexity-insight-MCP/dist/index.js"
            ],
            "cwd": "/path/to/perplexity-insight-MCP",
            "env": {
                "PERPLEXITY_API_KEY": "pplx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later