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
gptr-mcp-demo.mp4
research_resource: Get web resources related to a given task via research.
deep_research: Performs deep web research on a topic, finding the most reliable and relevant informationquick_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 herewrite_report: Generate a report based on research resultsget_research_sources: Get the sources used in the researchget_research_context: Get the full context of the research
research_query: Create a research query prompt
Before running the MCP server, make sure you have:
- Python 3.11 or higher installed
- Important: GPT Researcher >=0.12.16 requires Python 3.11+
- API keys for the services you plan to use:
- Clone the GPT Researcher repository:
git clone https://github.com/assafelovic/gpt-researcher.git
cd gpt-researcher- Install the gptr-mcp dependencies:
cd gptr-mcp
pip install -r requirements.txt- Set up your environment variables:
- Copy the
.env.examplefile to create a new file named.env:
cp .env.example .env
- Edit the
.envfile and add your API keys and configure other settings:
OPENAI_API_KEY=your_openai_api_key TAVILY_API_KEY=your_tavily_api_key
- Copy the
You can also add any other env variable for your GPT Researcher configuration.
You can run the MCP server in several ways:
python server.pymcp run server.pyThis is the simplest way to run the server if you don't need to connect to other containers:
# Build and run with docker-compose
docker-compose -f docker-compose.standalone.yml up -d
# Or manually:
docker build -t gpt-mcp-server .
docker run -d \
--name gpt-mcp-server \
-p 8000:8000 \
--env-file .env \
gpt-mcp-serverIf you need to connect to other services like n8n on the same network:
# Create the network if it doesn't exist
docker network create n8n-mcp-net
# Build and run with docker-compose
docker-compose up -d
# Or manually:
docker build -t gpt-mcp-server .
docker run -d \
--name gpt-mcp-server \
--network n8n-mcp-net \
-p 8000:8000 \
--env-file .env \
gpt-mcp-serverNote: 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:
- Accessing the OpenAPI docs at http://localhost:8000/docs
- Testing the MCP endpoint at http://localhost:8000/mcp
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.
To integrate your locally running MCP server with Claude for Mac, you'll need to:
- Make sure the MCP server is installed and running
- 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
- Restart Claude to apply the configuration
- Locate or create the configuration file at
For complete step-by-step instructions, see the Claude Desktop Integration guide.
User: I'm considering investing in NVIDIA. Can you research the current state of the company, recent stock performance, latest product announcements, and analyst opinions?
Claude: I'll help you research NVIDIA for investment purposes. This will take a moment as I conduct comprehensive research to find the most up-to-date information about their stock performance, recent developments, and expert analysis.
[Claude uses conduct_research tool - this takes 30-40 seconds]
Claude: Based on my research, here's a comprehensive analysis of NVIDIA's current state:
## NVIDIA (NVDA) Current Status
### Recent Stock Performance
- Current price: $942.89 (as of my research)
- YTD performance: +90.4%
- 52-week range: $460.30 - $974.00
- Market cap: ~$2.32 trillion
### Recent Key Developments
1. **Blackwell AI Platform**: At GTC 2024, NVIDIA unveiled the Blackwell architecture, their next-generation AI chip platform promising 4x performance improvement over Hopper. Major cloud providers (AWS, Google, Microsoft) have already committed to integrating Blackwell.
2. **Q1 FY2025 Earnings (May 2024)**:
- Revenue: $26.0 billion (+262% YoY)
- Data Center revenue: $22.6 billion (+427% YoY)
- Gross margin: 78.4%
- Announced 10-for-1 stock split effective June 7, 2024
3. **Supply Chain Expansion**: Increased investments in manufacturing capacity with TSMC to address ongoing chip shortages for their high-demand AI GPUs.
### Analyst Consensus
- Strong Buy consensus with 37 analysts rating it "Buy," 5 "Hold," and 0 "Sell"
- Average price target: $1,042 (post-split adjusted: $104.20)
- Key bull thesis: Continued AI infrastructure spending and NVIDIA's dominant position in AI chips
- Key bear concerns: Valuation, potential competition from AMD, Intel, and custom silicon from tech giants
### Industry Position
- Dominant in AI GPU market with estimated 80-90% market share
- Expanding ecosystem through CUDA software platform and industry partnerships
- Diversifying beyond chips with DGX Cloud, AI software platforms, and automotive solutions
If you encounter issues while running the MCP server:
- Make sure your API keys are correctly set in the
.envfile - Check that you're using Python 3.11 or higher (required by gpt-researcher >=0.12.16)
- Ensure all dependencies are installed correctly
- Check the server logs for error messages
If you're running with Docker and experiencing issues:
- Verify the container is running:
docker ps | grep gpt-mcp-server - Check container logs:
docker logs gpt-mcp-server - Confirm the server is binding to all interfaces - logs should show listening on 0.0.0.0:8000
- If you see dependency errors during build:
- Ensure you're using the updated Dockerfile with Python 3.11
- Try rebuilding with the
--no-cacheflag:docker build --no-cache -t gpt-mcp-server . - Check the version of gpt-researcher in your requirements.txt matches the Python version
For local installation issues:
# Check your Python version (must be 3.11+)
python --version
# Update pip to the latest version
pip install --upgrade pip
# If you're using a virtual environment, create a new one with Python 3.11
python3.11 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate- 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
This project is licensed under the MIT License - see the LICENSE file for details.