MCP-researcher Server

Provides Perplexity-powered research capabilities with context-aware conversations and code assistance for MCP workflows.

typescript

4

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "clssck-researcher-mcp": {
      "command": "node",
      "args": [
        "[path/to/researcher-mcp/build/index.js]"
      ],
      "env": {
        "PERPLEXITY_MODEL": "sonar-reasoning",
        "PERPLEXITY_API_KEY": "pplx-..."
      }
    }
  }
}

You have an MCP server called MCP-researcher Server that acts as a powerful research assistant. It integrates with Claude Desktop and leverages Perplexity AI to perform intelligent search, retrieve documentation, discover APIs, and help modernize code, all while you code.

How to use

Use this MCP server with your MCP client to perform structured research tasks while you work. It supports four core capabilities: searching for comprehensive information, retrieving detailed documentation and usage examples, discovering APIs suitable for your project, and checking deprecated code with migration guidance. You can authorize and interact with the server through your MCP client, and you can rely on its context-aware responses that maintain state across queries.

Key capabilities you should leverage: - Search to obtain broad or focused information with adjustable detail levels. - Get Documentation to fetch thorough docs, usage examples, best practices, and common pitfalls. - Find APIs to evaluate potential integrations, including features, pricing, and integration effort. - Check Deprecated Code to analyze code for outdated patterns and receive migration guidance.

Note on configuration and access

The server is designed to run locally or alongside your existing MCP clients. To connect, you use the provided MCP connection configuration that runs the Perplexity-backed researcher process and exposes its functionality to your client. The server exposes capabilities under a single configured runtime process and uses environment variables to manage API keys and model choices.

Examples of usage patterns

Start a research session and ask for background information on a topic, then drill down into documentation for a specific library. - Query for API options for a feature, compare options, and extract integration steps. - Input code snippets to check for deprecated patterns and receive migration guidance.

Available tools

search

Performs general search queries to gather information on any topic and returns results tailored to the requested detail level.

get_documentation

Retrieves documentation and usage examples for technologies, libraries, or APIs, including best practices and common pitfalls.

find_apis

Discovers and analyzes APIs suitable for integration into a project, including features, pricing, and integration complexity.

check_deprecated_code

Analyzes code for deprecated features or patterns and provides migration guidance to modern alternatives.