✨ From vibe coding to vibe deployment. UBOS MCP turns ideas into infra with one message.

Learn more

NIH RePORTER MCP

A Model Context Protocol (MCP) server for chatting with NIH RePORTER. Search for NIH-funded research projects and publications in a conversational manner. Accompanying blog post here.

img

Features

  • Search NIH-funded research projects with various criteria:
    • Fiscal years
    • Principal Investigator names
    • Organization details (name, state, city, type, department)
    • Funding amounts
    • COVID-19 response status
    • Funding mechanism
    • Institute/Center codes
    • RCDC terms
    • Date ranges
  • Search publications associated with NIH projects
  • Combined search functionality for both projects and publications
  • Detailed project and publication information including abstracts
  • Configurable result limits

Prerequisites

  • Python 3.12 or higher
  • UV package manager (recommended for faster dependency installation)

Installation

  1. Clone the repository:
git clone <repository-url>
cd mcp-nih-reporter
  1. Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate  # On Windows, use `.venvScriptsactivate`
  1. Install dependencies using UV:
uv pip install -e .

Usage

This MCP server provides access to the NIH RePORTER API through several tools:

  • search_projects: Search for NIH-funded research projects
  • search_publications: Search for publications associated with NIH projects
  • search_combined: Combined search for both projects and publications
  • test_connection: Test the API connection

You can use this MCP with any MCP-compatible client, such as:

  • Claude Desktop
  • Cursor
  • Other MCP-enabled tools

Example claude_desktop_config.json

{
  "mcpServers": {
	 "nih-reporter": {
	      "command": "<fully qualified path to>/uv",
	      "args": [
	        "run",
	        "--with",
	        "mcp[cli]",
	        "mcp",
	        "run",
	        "<fully qualified path to>/mcp-nih-reporter/mcp-nih-reporter.py"
	      ]
	    }
  }
}

The search results will be returned in a structured format containing project details including:

  • Project title and abstract
  • Principal Investigator information
  • Organization details
  • Funding information
  • Project dates and status

Debugging

A log file will be created in the root folder when the MCP attempts to run in a client (e.g. Claude Desktop). Check there if you’re having trouble.

Development

The project uses:

  • httpx for async HTTP requests
  • mcp for the Mission Control Protocol implementation
  • python-dotenv for environment variable management
  • uv for dependency management

Logging

Logs are written to mcp-nih-reporter.log in the project root directory. The logging level is set to INFO by default.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Please make sure to update tests as appropriate and follow the existing code style.

License

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

Featured Templates

View More
AI Assistants
Image to text with Claude 3
152 1366
AI Assistants
Talk with Claude 3
159 1523
AI Agents
AI Video Generator
252 2007 5.0

Start your free trial

Build your solution today. No credit card required.

Sign In

Register

Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.