Frequently Asked Questions

Q: What is an MCP Server?

A: MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). An MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools.

Q: How does the UBOS Asset Marketplace MCP Server work?

A: The MCP server integrates with Claude Desktop to query clinicaltrials.gov based on genetic mutations. It retrieves trial data, summarizes key information, and returns the results to the user.

Q: What genetic mutations are supported?

A: The server supports a wide range of genetic mutations, and the UBOS team is continuously expanding the coverage. Check the documentation for a complete list of supported mutations.

Q: Can I use this server without Claude Desktop?

A: The server is specifically designed to integrate with Claude Desktop. While it’s technically possible to use it with other AI models, it may require significant modifications.

Q: How do I install and configure the MCP server?

A: The project includes detailed installation instructions in the documentation. Follow these instructions to set up the server and configure it with Claude Desktop.

Q: What are the dependencies for this project?

A: The project requires Python 3.7+, PocketFlow, MCP SDK, Requests, and Python-dotenv. All dependencies can be installed using uv.

Q: Where can I find more information about the project?

A: The project includes extensive documentation, including a design document, future work document, and a guide to using Context7. These documents provide detailed information about the server’s architecture, features, and usage.

Q: Is this project suitable for medical decision-making?

A: No, this project is a prototype and is intended for research and demonstration purposes only. It should not be used to make medical decisions or as a substitute for professional medical advice.