NIH RePORTER MCP
A Model Context Protocol server that enables conversational searching of NIH-funded research projects and publications through the NIH RePORTER database.
README
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.

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
- Clone the repository:
git clone <repository-url>
cd mcp-nih-reporter
- Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate # On Windows, use `.venv\Scripts\activate`
- 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 projectssearch_publications: Search for publications associated with NIH projectssearch_combined: Combined search for both projects and publicationstest_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:
httpxfor async HTTP requestsmcpfor the Mission Control Protocol implementationpython-dotenvfor environment variable managementuvfor 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.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - 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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.