Perplexity Ask MCP Server

What does “Perplexity Ask” MCP Server do?

The Perplexity Ask MCP Server is a Model Context Protocol (MCP) server implementation that integrates the Sonar API, enabling real-time, web-wide research capabilities within the MCP ecosystem. By connecting AI assistants like Claude to the Perplexity API, it allows developers and users to perform live web searches and access up-to-date information directly through their development workflows. This seamless integration makes it possible to enhance AI-powered applications with dynamic data retrieval, enabling tasks such as live question answering, research, and information gathering without leaving the MCP environment. The server serves as a connector, bridging AI assistants with Perplexity’s web search capabilities for a more informed and interactive user experience.

List of Prompts

No prompt templates are mentioned in the available documentation or repository files.

List of Resources

No explicit resources are listed in the documentation or repository files.

List of Tools

• perplexity_ask
  • Engages in a conversation with the Sonar API for live web searches.
  • Inputs:
    • messages (array): An array of conversation messages, each with:
      • role (string): The role of the message (e.g., system, user, assistant).
      • content (string): The content of the message.

Use Cases of this MCP Server

• Real-Time Web Search for AI Assistants
  • Enables AI assistants (like Claude) to access and retrieve live information from the web, supporting up-to-date research and information synthesis within conversations.
• Automated Question Answering
  • Allows automated systems to respond to user queries with current, web-sourced answers, enhancing the accuracy and relevance of chatbot and virtual assistant responses.
• Research Support
  • Facilitates rapid, comprehensive information gathering for developers, researchers, and knowledge workers without leaving their development environment.
• Integration in Developer Workflows
  • Embeds web search functionality directly into tools such as Claude Desktop and Cursor, streamlining development and research tasks.
• Knowledge Augmentation
  • Supplements LLMs with external, up-to-date data, improving their performance in tasks requiring recent or specific information.

How to set it up

Windsurf

No explicit Windsurf setup instructions provided in the documentation.

Claude

1. Prerequisites: Download Claude Desktop from here.
2. Get a Sonar API Key: Sign up for a Sonar API account, and generate your API key.
3. Edit Configuration File: Locate and edit claude_desktop_config.json (e.g., using vim ~/Library/Application\ Support/Claude/claude_desktop_config.json).
4. Add MCP Server: Insert the following JSON configuration:

{
  "mcpServers": {
    "perplexity-ask": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PERPLEXITY_API_KEY",
        "mcp/perplexity-ask"
      ],
      "env": {
        "PERPLEXITY_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

5. Save and Restart: Save the configuration and restart Claude Desktop.
6. Verify Setup: Look for the hammer icon and ensure the “perplexity-ask” tool appears.

Securing API Keys: Place PERPLEXITY_API_KEY in the env field as shown above.

Cursor

1. Navigate to Settings in Cursor.
2. Go to MCP Directory and click “Add new global MCP server.”
3. Insert MCP Server Configuration (use the same JSON as in Claude setup).
4. Save Settings.
5. Verify Integration: The tool should appear in your available tools.

Securing API Keys: Use the env field in the configuration.

Cline

No explicit Cline setup instructions provided in the documentation.

Generic NPX Example

{
  "mcpServers": {
    "perplexity-ask": {
      "command": "npx",
      "args": [
        "-y",
        "server-perplexity-ask"
      ],
      "env": {
        "PERPLEXITY_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Note: Always secure API keys using the env field in your configuration.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "perplexity-ask": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “perplexity-ask” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: Not mentioned
Sampling support: Not mentioned

Our opinion

Perplexity Ask MCP Server is focused and well-documented for integrating web search into LLM workflows, but lacks documented prompt templates or resource primitives. Setup instructions are clear for Claude and Cursor, and the single tool is powerful for research tasks. Overall, the repo is robust and well-used but limited in breadth of MCP primitives.

MCP Score