drio
Open app

perplexity-mcp MCP server

Source

A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API.

Catalog onlyCatalog onlySTDIO

Overview

perplexity-mcp is a Model Context Protocol (MCP) server that enables web search functionality using the Perplexity AI's API, designed to work seamlessly with the Anthropic Claude desktop client.

To use perplexity-mcp, install the server via the Fast Python package manager 'uv', configure your API key, and integrate it into the Claude desktop client configuration, allowing you to search the web with specific prompts.

  • Direct web search capabilities leveraging Perplexity AI's API - Customizable query inputs with options for recent data filtering (last day, week, month, year) - Easy installation and configuration for use with the Claude desktop client
  1. Quickly retrieving the latest news about specific topics from the web.
  2. Supporting research by filtering results based on recency.
  3. Enhancing productivity tools by integrating advanced search functionalities into applications.

Add to your AI client

Use these steps to connect perplexity-mcp MCP server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "perplexity-mcp-jsonallen": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-perplexity-mcp-jsonallen"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "perplexity-mcp-jsonallen": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-perplexity-mcp-jsonallen"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "perplexity-mcp-jsonallen": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-perplexity-mcp-jsonallen"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "perplexity-mcp-jsonallen": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-perplexity-mcp-jsonallen"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "perplexity-mcp-jsonallen": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-perplexity-mcp-jsonallen"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "perplexity-mcp-jsonallen": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-perplexity-mcp-jsonallen"
      ]
    }
  }
}

FAQ

What do I need to get started with perplexity-mcp?

You need to have the 'uv' package installed, Perplexity AI API key, and the Claude desktop client configured to utilize this MCP server.

Can I filter search results based on time?

Yes! You can specify time filters for searching within the last day, week, month, or year.

Is perplexity-mcp free to use?

While the installation is free, you may need to check if the Perplexity AI service incurs any fees based on usage.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":487,"uuid":"ff9da30d-86a9-440c-987b-26412d258228","name":"perplexity-mcp","title":"perplexity-mcp MCP server","description":"A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API.","avatar_url":"https://avatars.githubusercontent.com/u/1411223?v=4","created_at":"2024-12-30T02:51:28.367Z","updated_at":"2025-01-05T02:54:45.491Z","status":"created","author_name":"jsonallen","author_avatar_url":"https://avatars.githubusercontent.com/u/1411223?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/jsonallen/perplexity-mcp","target":"_self","content":"$29","summary":"$2a","img_url":"https://camo.githubusercontent.com/589d6ecd2858102e0dd35510ceef800d1f99b43b7defa0eb9b95a1d79f2e6df4/68747470733a2f2f736d6974686572792e61692f62616467652f706572706c65786974792d6d6370","type":null,"metadata":"{\"star\":\"70\",\"license\":\"MIT license\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-03-19 10:59:45\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data