▌BestMCPTools.org
Perplexity MCP logo

Perplexity MCP

Give your AI agent live web search and deep research via Perplexity's Sonar API

SearchFreemiumClaudeCursorWindsurfVS Coden8nEasy✓ Verified
Own Perplexity MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

Active
Last code update: September 25, 2026License: MITChecked September 28, 2026

How to Install Perplexity MCP

$npx @modelcontextprotocol/inspector perplexity-mcp

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

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

Cursor (~/.cursor/mcp.json)

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

VS Code (.vscode/mcp.json)

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

Claude Code (terminal)

claude mcp add perplexity-mcp -- npx @modelcontextprotocol/inspector perplexity-mcp

Add any API keys or environment variables the server's README lists.

About Perplexity MCP

The official Perplexity MCP server connects AI assistants to Perplexity's Sonar API, enabling real-time web search with cited sources and the sonar-deep-research model for comprehensive multi-step research tasks. It returns grounded, citation-backed answers rather than hallucinated responses, making it the go-to MCP for any agent that needs current information from the web.

Perplexity MCP is a Search MCP server designed for researchers, analysts, and engineers building grounded agents. It enables giving AI assistants live, source-grounded web access by wrapping a search provider and page-fetch step as MCP tools. Key capabilities include live web search with snippets and urls, optional full-page fetch for cited sources, configurable result counts and freshness windows, and structured tool calls that work cleanly inside an LLM context. It integrates with Google, Bing, Brave, Tavily, Exa, Perplexity, and SerpAPI, and is best suited for researchers, analysts, and engineers building grounded agents who need research and competitive analysis.

Key Features

  • search
  • web-search
  • research
  • real-time
  • citations

Pricing

Freemium: from Free tier available, paid from $0.001/1k tokens

Pros & Cons

Pros

  • Lets the assistant answer about events past its training cutoff
  • Cites sources you can actually click
  • Replaces most simple RAG pipelines

Cons

  • Quality depends on the underlying search provider
  • Token costs scale with how much page content you pull
  • Rate limits can bite on bursty agent runs

Best For

  • Research and competitive analysis
  • Source-grounded answers in chat UIs
  • Fact-checking long-form drafts
  • Replacing manual Googling in agent loops

Our Take on Perplexity MCP

Perplexity MCP is the best way to give any AI agent access to current, cited web information: essential for any agent that needs up-to-date knowledge.

Alternatives to Perplexity MCP

Brave Search MCPSearch

Brave's own MCP server: web, news, image, video and place search plus LLM context

View Brave Search MCP →
Exa MCPSearch

AI-native semantic web search for agents

View Exa MCP →
Tavily MCPSearch

Real-time web search optimized for AI agents

View Tavily MCP →

Frequently Asked Questions

Tags