gptr-mcp

Overview

GPT Researcher MCP is a Python-based server that enables LLM applications to perform deep research through the MCP protocol. Unlike standard search tools that return raw results, this server autonomously explores and validates sources to deliver high-quality, comprehensive research. It offers both quick search for speed and deep research for thoroughness, along with report generation capabilities. The server supports multiple transport protocols including STDIO for local development and SSE for Docker/web deployments.

Try asking AI

After installing, here are 7 things you can ask your AI assistant:

• research_resource

  Get web resources related to a given task via research.

  Try:Find web resources about renewable energy investmentsTry:Get resources related to AI ethics in healthcare
• deep_research

  Performs deep web research on a topic, finding the most reliable and relevant information.

  Try:Research the latest developments in quantum computingTry:Investigate climate change impacts on coastal cities
• quick_search

  Performs a fast web search optimized for speed over quality.

  Try:Quick search for recent tech newsTry:Fast search for Python tutorials
• write_report

  Generate a report based on research results.

  Try:Write a report summarizing the research findingsTry:Generate a comprehensive report on market trends
• get_research_sources

  Get the sources used in the research.

  Try:Show me all the sources used for this researchTry:Get the research references for my query
• get_research_context

  Get the full context of the research.

  Try:Provide the full research contextTry:Show me all the research material
• research_query

  Create a research query prompt.

  Try:Help me formulate a research query about blockchain technologyTry:Create a query to research stock market trends

Comparable tools

Installation

git clone https://github.com/assafelovic/gpt-researcher.git
cd gpt-researcher/cd gptr-mcp

pip install -r requirements.txt

cp .env.example .env
# Edit .env with your API keys

{
  "mcpServers": {
    "gptr-mcp": {
      "command": "python",
      "args": ["/absolute/path/to/gptr-mcp/server.py"],
      "env": {
        "OPENAI_API_KEY": "your-openai-key-here",
        "TAVILY_API_KEY": "your-tavily-key-here"
      }
    }
  }
}

FAQ

What's the difference between deep research and quick search?

Deep research autonomously explores and validates numerous sources to deliver comprehensive, high-quality information (takes ~30 seconds). Quick search performs a fast web search optimized for speed over quality, returning basic search results with snippets.

What API keys are required?

You need an OpenAI API key for the LLM and a Tavily API key for web search. Other search engines can be configured if needed.

Compare gptr-mcp with