MCP Researcher Server

🚀 Perplexity MCP Server

An intelligent research assistant powered by Perplexity's professional AI models. It features automatic query complexity detection and routes requests to the most suitable model for optimal results. Unlike the official server, it has search capabilities for every task.

🚀 Quick Start

The Perplexity MCP Server is an intelligent research assistant that leverages Perplexity's advanced AI models. It can automatically detect query complexity and route requests to the most appropriate model, ensuring high - quality results.

✨ Features

Tools

⚠️ Important Note

Due to implementation differences, when using certain tools (such as cline) with the Reason tool, timeouts may occur compared to other tools like cursor. However, the reason tool compensates for this issue.

1. Search (Sonar Pro)

Quickly search for simple queries and perform basic information lookup. It is most suitable for straightforward questions that require concise and direct answers.

const result = await use_mcp_tool({
  server_name: "perplexity",
  tool_name: "search",
  arguments: {
    query: "法国的首都是哪里？",
    force_model: false // Optional: Force using this model even if the query seems complex
  }
});

2. Reasoning (Sonar Reasoning Pro)

Handle complex multi - step tasks that require detailed analysis. It is ideal for explanations, comparisons, and problem - solving.

const result = await use_mcp_tool({
  server_name: "perplexity",
  tool_name: "reason",
  arguments: {
    query: "比较和对比 REST 和 GraphQL API，解释它们的优缺点",
    force_model: false // Optional: Force using this model even if the query seems simple
  }
});

3. In - depth Research (Sonar In - depth Research)

Conduct comprehensive research and generate detailed reports. It is very suitable for in - depth analysis of complex topics.

const result = await use_mcp_tool({
  server_name: "perplexity",
  tool_name: "deep_research",
  arguments: {
    query: "量子计算对密码学的影响",
    focus_areas: [
      "后量子加密算法",
      "量子威胁的时间表",
      "实际缓解策略"
    ],
    force_model: false // Optional: Force using this model even if the query seems simple
  }
});

Intelligent Model Selection

The server automatically analyzes query complexity to route requests to the most suitable model:

1. Simple Queries → Sonar Pro

   • Basic information lookup
   • Direct questions
   • Quick facts

2. Complex Queries → Sonar Reasoning Pro

   • How/Why questions
   • Comparisons
   • Step - by - step explanations
   • Problem - solving tasks

3. Research Queries → Sonar In - depth Research

   • In - depth analysis
   • Comprehensive research
   • Detailed investigations
   • Multi - faceted topics

You can override the automatic selection by using force_model: true in the parameters of any tool.

📦 Installation

Prerequisites

• Node.js (from nodejs.org)
• Perplexity API key (from perplexity.ai/settings/api)
• Clone this repository to a local location

Configure MCP Settings

Add the following to your MCP settings file (location may vary depending on the platform):

{
  "mcpServers": {
    "perplexity": {
      "command": "node",
      "args": ["/path/to/perplexity-server/build/index.js"],
      "env": {
        "PERPLEXITY_API_KEY": "YOUR_API_KEY_HERE"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Or use NPX without local installation (recommended for macOS):

{
  "mcpServers": {
    "perplexity": {
      "command": "npx",
      "args": [
        "-y",
        "perplexity-mcp"
      ],
      "env": {
        "PERPLEXITY_API_KEY": "your_api_key"
      }
    }
  }
}