perplexity-mcp

MCP.Pizza Chef: jsonallen

perplexity-mcp is a Model Context Protocol (MCP) server that integrates web search capabilities into LLM workflows by leveraging Perplexity AI's API. It allows models to perform real-time internet searches with customizable recency filters (day, week, month), providing up-to-date information directly within the MCP ecosystem. Compatible with clients like Anthropic Claude desktop, it empowers AI agents to access fresh web data for improved context and decision-making. This server is ideal for developers seeking to augment language models with live search results, enabling dynamic, informed responses based on the latest online content.

Use This MCP server To

Enable LLMs to perform real-time web searches Filter search results by recency (day, week, month) Integrate live internet data into AI workflows Enhance AI assistants with up-to-date web knowledge Support dynamic query answering with fresh search results

README

perplexity-mcp MCP server

smithery badge

A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API. Works with the Anthropic Claude desktop client.

Example

Let's you use prompts like, "Search the web to find out what's new at Anthropic in the past week."

Glama Scores

Perplexity Server MCP server

Components

Prompts

The server provides a single prompt:

  • perplexity_search_web: Search the web using Perplexity AI
    • Required "query" argument for the search query
    • Optional "recency" argument to filter results by time period:
      • 'day': last 24 hours
      • 'week': last 7 days
      • 'month': last 30 days (default)
      • 'year': last 365 days
    • Uses Perplexity's API to perform web searches

Tools

The server implements one tool:

  • perplexity_search_web: Search the web using Perplexity AI
    • Takes "query" as a required string argument
    • Optional "recency" parameter to filter results (day/week/month/year)
    • Returns search results from Perplexity's API

Installation

Installing via Smithery

To install Perplexity MCP for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install perplexity-mcp --client claude

Requires UV (Fast Python package and project manager)

If uv isn't installed.

# Using Homebrew on macOS
brew install uv

or

# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows.
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Environment Variables

The following environment variable is required in your claude_desktop_config.json. You can obtain an API key from Perplexity

  • PERPLEXITY_API_KEY: Your Perplexity AI API key

Optional environment variables:

  • PERPLEXITY_MODEL: The Perplexity model to use (defaults to "sonar" if not specified)

    Available models:

    • sonar-deep-research: 128k context - Enhanced research capabilities
    • sonar-reasoning-pro: 128k context - Advanced reasoning with professional focus
    • sonar-reasoning: 128k context - Enhanced reasoning capabilities
    • sonar-pro: 200k context - Professional grade model
    • sonar: 128k context - Default model
    • r1-1776: 128k context - Alternative architecture

And updated list of models is avaiable (here)[https://docs.perplexity.ai/guides/model-cards]

Cursor & Claude Desktop Installation

Add this tool as a mcp server by editing the Cursor/Claude config file.

  "perplexity-mcp": {
    "env": {
      "PERPLEXITY_API_KEY": "XXXXXXXXXXXXXXXXXXXX",
      "PERPLEXITY_MODEL": "sonar"
    },
    "command": "uvx",
    "args": [
      "perplexity-mcp"
    ]
  }

Cursor

  • On MacOS: /Users/your-username/.cursor/mcp.json
  • On Windows: C:\Users\your-username\.cursor\mcp.json

If everything is working correctly, you should now be able to call the tool from Cursor. mcp_screenshot

Claude Desktop

  • On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
  • On Windows: %APPDATA%/Claude/claude_desktop_config.json

To verify the server is working. Open the Claude client and use a prompt like "search the web for news about openai in the past week". You should see an alert box open to confirm tool usage. Click "Allow for this chat".

mcp_screenshot

perplexity-mcp FAQ

How do I configure the perplexity-mcp server to use Perplexity AI's API?
You need to provide your Perplexity AI API credentials in the server configuration to enable authenticated web search requests.
Can I filter search results by time period using perplexity-mcp?
Yes, the server supports an optional 'recency' argument allowing filtering by last day, week, or month.
Is perplexity-mcp compatible with multiple MCP clients?
It is designed to work with MCP clients like Anthropic Claude desktop and can be integrated with others supporting MCP protocol.
What kind of queries can I run through perplexity-mcp?
You can run natural language search queries to retrieve relevant web results, such as recent news or specific topic information.
Does perplexity-mcp cache search results?
The server primarily fetches live data from Perplexity AI; caching behavior depends on server implementation and configuration.
How does perplexity-mcp handle API rate limits?
Rate limiting is managed according to Perplexity AI's API policies; users should monitor usage to avoid exceeding limits.
Can perplexity-mcp be extended with additional search parameters?
Currently, it supports query and recency filters; extending parameters would require modifying the server code.
Which LLM providers can benefit from perplexity-mcp?
Models from OpenAI, Anthropic Claude, and Google Gemini can leverage this server for enhanced web search context.