GPT Researcher MCP Server

🔍 GPT Researcher MCP Server

Why GPT Researcher MCP?

While LLM apps can access web search tools with MCP, GPT Researcher MCP delivers deep research results. Standard search tools return raw results requiring manual filtering, often containing irrelevant sources and wasting context window space.

GPT Researcher autonomously explores and validates numerous sources, focusing only on relevant, trusted and up-to-date information. Though slightly slower than standard search (~30 seconds wait), it delivers:

• ✨ Higher quality information
• 📊 Optimized context usage
• 🔎 Comprehensive results
• 🧠 Better reasoning for LLMs

💻 Claude Desktop Demo

https://github.com/user-attachments/assets/ef97eea5-a409-42b9-8f6d-b82ab16c52a8

🚀 Quick Start with Claude Desktop

Want to use this with Claude Desktop right away? Here's the fastest path:

1. Install dependencies:
   git clone https://github.com/assafelovic/gptr-mcp.git pip install -r requirements.txt
2. Set up your Claude Desktop config at ~/Library/Application Support/Claude/claude_desktop_config.json:
   { "mcpServers": { "gptr-mcp": { "command": "python", "args": ["/absolute/path/to/gpt-researcher/gptr-mcp/server.py"], "env": { "OPENAI_API_KEY": "your-openai-key-here", "TAVILY_API_KEY": "your-tavily-key-here" } } } }
3. Restart Claude Desktop and start researching! 🎉

For detailed setup instructions, see the full Claude Desktop Integration section below.

Resources

• research_resource: Get web resources related to a given task via research.

Primary Tools

• deep_research: Performs deep web research on a topic, finding the most reliable and relevant information
• quick_search: Performs a fast web search optimized for speed over quality, returning search results with snippets. Supports any GPTR supported web retriever such as Tavily, Bing, Google, etc... Learn more here
• write_report: Generate a report based on research results
• get_research_sources: Get the sources used in the research
• get_research_context: Get the full context of the research

Prompts

• research_query: Create a research query prompt

Prerequisites

Before running the MCP server, make sure you have:

1. Python 3.11 or higher installed
   • Important: GPT Researcher >=0.12.16 requires Python 3.11+
2. API keys for the services you plan to use:
   • OpenAI API key
   • Tavily API key

You can also connect any other web search engines or MCP using GPTR supported retrievers. Check out the docs here

⚙️ Installation

1. Clone the GPT Researcher repository:

2. Install the gptr-mcp dependencies:

3. Set up your environment variables:
   • Copy the .env.example file to create a new file named .env:
   cp .env.example .env
   • Edit the .env file and add your API keys and configure other settings:
   OPENAI_API_KEY=your_openai_api_key TAVILY_API_KEY=your_tavily_api_key

You can also add any other env variable for your GPT Researcher configuration.

🚀 Running the MCP Server

You can run the MCP server in several ways:

Method 1: Directly using Python

Method 2: Using the MCP CLI (if installed)

Method 3: Using Docker (recommended for production)

Quick Start

The simplest way to run with Docker:

For n8n Integration

If you need to connect to an existing n8n network:

Note: The Docker image uses Python 3.11 to meet the requirements of gpt-researcher >=0.12.16. If you encounter errors during the build, ensure you're using the latest Dockerfile from this repository.

Once the server is running, you'll see output indicating that the server is ready to accept connections. You can verify it's working by:

1. SSE Endpoint: Access the Server-Sent Events endpoint at http://localhost:8000/sse to get a session ID
2. MCP Communication: Use the session ID to send MCP messages to http://localhost:8000/messages/?session_id=YOUR_SESSION_ID
3. Testing: Run the test script with python test_mcp_server.py

Important for Docker/n8n Integration:

• The server binds to 0.0.0.0:8000 to work with Docker containers
• Uses SSE transport for web-based MCP communication
• Session management requires getting a session ID from /sse endpoint first
• Each client connection needs a unique session ID for proper communication

🚦 Transport Modes & Best Practices

The GPT Researcher MCP server supports multiple transport protocols and automatically chooses the best one for your environment:

Transport Types

Automatic Detection

The server automatically detects your environment:

Environment Variables

Configuration Examples

For Claude Desktop (Local)

For Docker/Web Deployment

For n8n MCP Integration

Transport Endpoints

When using SSE or HTTP transports:

• Health Check: GET /health
• SSE Endpoint: GET /sse (get session ID)
• MCP Messages: POST /messages/?session_id=YOUR_SESSION_ID

Best Practices

1. Local Development: Use default STDIO for Claude Desktop
2. Production: Use Docker with automatic SSE detection
3. Testing: Use health endpoints to verify connectivity
4. n8n Integration: Always use container networking with Docker
5. Web Deployment: Consider Streamable HTTP for modern clients

Integrating with Claude

You can integrate your MCP server with Claude using:

Claude Desktop Integration - For using with Claude desktop application on Mac

For detailed instructions, follow the link above.

💻 Claude Desktop Integration

To integrate your locally running MCP server with Claude for Mac, you'll need to:

1. Make sure the MCP server is installed and running
2. Configure Claude Desktop:
   • Locate or create the configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json
   • Add your local GPT Researcher MCP server to the configuration with environment variables
   • Restart Claude to apply the configuration

⚠️ Important: Environment Variables Required

Claude Desktop launches your MCP server as a separate subprocess, so you must explicitly pass your API keys in the configuration. The server cannot access your shell's environment variables or .env file automatically.

Configuration Example

Security Note

🔒 Your Claude Desktop config contains sensitive API keys. Protect it:

Never commit this file to version control.

Alternative: Environment Variable Script

For better security, create a wrapper script:

run_gptr_mcp.sh:

Then use it in Claude Desktop:

For complete step-by-step instructions, see the Claude Desktop Integration guide.

📝 Example Usage with Claude

🔧 Troubleshooting

If you encounter issues while running the MCP server:

General Issues

1. API Keys: Make sure your API keys are correctly set in the .env file
2. Python Version: Check that you're using Python 3.11 or higher (required by gpt-researcher >=0.14.0)
3. Dependencies: Ensure all dependencies are installed correctly: pip install -r requirements.txt
4. Server Logs: Check the server logs for error messages

Docker Issues

1. Container not accessible:
   • Verify the container is running: docker ps | grep gptr-mcp
   • Check container logs: docker logs gptr-mcp
   • Confirm the server is binding to 0.0.0.0:8000 (logs should show this)
2. n8n Integration Issues:
   • Ensure both containers are on the same Docker network
   • Use the container name gptr-mcp as the hostname in n8n
   • Set the MCP server URL to: http://gptr-mcp:8000/sse
3. Session ID Issues:
   • The server uses SSE transport which requires session management
   • First, get a session ID by connecting to /sse endpoint
   • Use the session ID in subsequent MCP requests: /messages/?session_id=YOUR_ID
   • Each client needs its own session ID

n8n MCP Integration Steps

1. Get Session ID:
   curl http://gptr-mcp:8000/sse # Look for: data: /messages/?session_id=XXXXX
2. Initialize MCP:
   curl -X POST http://gptr-mcp:8000/messages/?session_id=YOUR_SESSION_ID \ -H "Content-Type: application/json" \ -d '{"jsonrpc": "2.0", "id": 1, "method": "initialize", "params": {"protocolVersion": "2024-11-05", "capabilities": {"roots": {"listChanged": true}}, "clientInfo": {"name": "n8n-client", "version": "1.0.0"}}}'
3. Call Tools:
   curl -X POST http://gptr-mcp:8000/messages/?session_id=YOUR_SESSION_ID \ -H "Content-Type: application/json" \ -d '{"jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": {"name": "quick_search", "arguments": {"query": "test"}}}'

Testing the Server

Run the included test script to verify functionality:

This will test:

• SSE connection and session ID retrieval
• MCP initialization
• Tool discovery and execution

Claude Desktop Issues

If your MCP server isn't working with Claude Desktop:

1. Server not appearing in Claude:
   • Check your claude_desktop_config.json syntax is valid JSON
   • Ensure you're using absolute paths (not relative)
   • Verify the path to server.py is correct
   • Restart Claude Desktop completely
2. "OPENAI_API_KEY not found" error:
   • Make sure you added API keys to the env section in your config
   • Don't forget both OPENAI_API_KEY and TAVILY_API_KEY
   • API keys should be the actual keys, not placeholders
3. Tools not showing up:
   • Look for the 🔧 tools icon in Claude Desktop
   • Check that Claude Desktop config file is in the right location:
     • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
     • Windows: %APPDATA%\Claude\claude_desktop_config.json
4. Python/Permission issues:
   • Make sure Python is accessible from the command line: python --version
   • Try using full Python path: "command": "/usr/bin/python3" or "command": "python3"
   • Check file permissions on your server.py file
5. Still not working?
   • Test the server manually: python server.py (should show STDIO transport message)
   • Check Claude Desktop logs (if available)
   • Try the alternative script method from the integration section above

👣 Next Steps

• Explore the MCP protocol documentation to better understand how to integrate with Claude
• Learn about GPT Researcher's core features to enhance your research capabilities
• Check out the Advanced Usage guide for more configuration options

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

📞 Support / Contact

• Community Discord
• Email: assaf.elovic@gmail.com