Perplexity AI Search MCP server

This MCP server integrates Perplexity AI's API to provide advanced search capabilities through various models, offering a powerful way to access Perplexity's search technology through the Model Context Protocol.

Installation

To install the Perplexity AI MCP server, follow these steps:

pnpm install
pnpm build

Configuration

Before using the server, you need to configure your Perplexity AI API key.

API Key Setup

1. Sign up for a Perplexity AI account
2. Get your API key from the dashboard
3. Set the environment variable:

export PERPLEXITY_API_KEY=your_api_key_here

Running the Server

Once installed and configured, you can run the server using one of these methods:

node dist/index.js
# or if you made it executable
./dist/index.js

Available Models

The server supports all official Perplexity Sonar models:

• sonar-reasoning-pro (127k context)
• sonar-reasoning (127k context)
• sonar-pro (200k context)
• sonar (127k context)

Using the Search Tool

perplexity_search

The main functionality is provided through the perplexity_search tool which performs searches using Perplexity AI's models.

Parameters:

• query (string, required): The search query
• model (string, optional): Model to use (default: "sonar")
  • Available options: sonar-reasoning-pro, sonar-reasoning, sonar-pro, sonar
• count (number, optional): Number of results (1-10, default: 5)

Testing with MCP Inspector

To test your implementation using the MCP Inspector tool:

pnpm inspect

This allows you to verify that your server correctly implements the MCP protocol and responds to queries as expected.

Additional Features

• Configurable result count (1-10 results)
• Detailed error handling and logging
• Compatible with MCP Inspector for verification
• Logs are written to perplexity-mcp.log in the project root directory

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-ai-search" '{"command":"node","args":["dist/index.js"]}'

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-ai-search": {
            "command": "node",
            "args": [
                "dist/index.js"
            ]
        }
    }
}

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-ai-search": {
            "command": "node",
            "args": [
                "dist/index.js"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect