Cover image
Try Now
2025-03-31

MCP server for enabling LLM applications to perform deep research via the MCP protocol

3 years

Works with Finder

1

Github Watches

3

Github Forks

83

Github Stars

Logo

🔍 GPT Researcher MCP Server

Website Documentation Discord Follow

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

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 3.10 or higher installed
  2. API keys for the services you plan to use:

⚙️ Installation

  1. Clone the GPT Researcher repository:
git clone https://github.com/assafelovic/gpt-researcher.git
cd gpt-researcher
  1. Install the gptr-mcp dependencies:
cd gptr-mcp
pip install -r requirements.txt
  1. 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 start the MCP server in two ways:

Method 1: Directly using Python

python server.py

Method 2: Using the MCP CLI (if installed)

mcp run server.py

Once the server is running, you'll see output indicating that the server is ready to accept connections.

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
    • Restart Claude to apply the configuration

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

📝 Example Usage with Claude

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

🔧 Troubleshooting

If you encounter issues while running the MCP server:

  1. Make sure your API keys are correctly set in the .env file
  2. Check that you're using Python 3.10 or higher
  3. Ensure all dependencies are installed correctly
  4. Check the server logs for error messages

👣 Next Steps

📄 License

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

📞 Support / Contact

⬆️ Back to Top

相关推荐

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • https://zenepic.net
  • Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • 林乔安妮
  • A fashion stylist GPT offering outfit suggestions for various scenarios.

  • https://reddgr.com
  • Delivers concise Python code and interprets non-English comments

  • 田中 楓太
  • A virtual science instructor for engaging and informative lessons.

  • 1Panel-dev
  • 💬 MaxKB is a ready-to-use AI chatbot that integrates Retrieval-Augmented Generation (RAG) pipelines, supports robust workflows, and provides advanced MCP tool-use capabilities.

  • ShrimpingIt
  • Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx

  • Dhravya
  • Collection of apple-native tools for the model context protocol.

  • GLips
  • MCP server to provide Figma layout information to AI coding agents like Cursor

  • open-webui
  • User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

  • Mintplex-Labs
  • The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

  • adafruit
  • Python code to use the MCP3008 analog to digital converter with a Raspberry Pi or BeagleBone black.

    Reviews

    4 (1)
    Avatar
    user_R8raH1VH
    2025-04-17

    As a devoted user of the gptr-mcp application, I am thoroughly impressed with its seamless integration and robust functionality. Developed by assafelovic, this tool has greatly enhanced my productivity with its efficient performance and user-friendly interface. The extensive documentation and support available at https://github.com/assafelovic/gptr-mcp are very helpful, making it easy for even beginners to navigate. Highly recommended for anyone in need of a reliable MCP solution!