What is the ClinicalTrials MCP Server?

The ClinicalTrials MCP Server is a tool that enables AI assistants to search and access data from ClinicalTrials.gov through a simple Model Context Protocol (MCP) interface.

What is MCP?

MCP stands for Model Context Protocol. It’s a standard that allows applications to provide context to Large Language Models (LLMs), enabling them to interact with external data sources and tools.

How does the ClinicalTrials MCP Server work?

It acts as a bridge between AI models and the ClinicalTrials.gov repository, allowing AI models to search for clinical trials and access their content programmatically.

What are the core features of the ClinicalTrials MCP Server?

Core features include trial search, efficient retrieval of data, metadata access, research support, CSV management, local storage for faster access, and statistics generation.

How can I install the ClinicalTrials MCP Server?

You can install it via Smithery or manually using uv. Instructions are provided in the documentation.

What tools are provided by the ClinicalTrials MCP Server?

The server provides tools like search_clinical_trials_and_save_studies_to_csv, get_full_study_details, get_studies_by_keyword, get_study_statistics, get_full_studies_and_save, load_csv_data, and list_saved_csv_files.

Can you give some examples of how to use the tools?

Examples include searching for clinical trials related to COVID-19 vaccine efficacy and saving the results to a CSV, getting studies by keyword (e.g., diabetes), and getting full study details for a specific trial using its NCT ID.

What resources are provided by the ClinicalTrials MCP Server?

Resources include access to corona fields data, full studies data, data from specific CSV files, a list of available CSV files, a specific study by NCT ID, and studies related to a specific condition.

How can I use the ClinicalTrials MCP Server with Claude Desktop?

You can add a configuration to your claude_desktop_config.json file. Example configurations for Mac OS and Windows are provided in the documentation.

What capabilities are available after integrating with Claude Desktop?

You can ask Claude to search for clinical trials and get trial details, such as the trial title, NCT Number, conditions, and brief summary.

What are the dependencies for the ClinicalTrials MCP Server?

The dependencies include Python 3.10+, FastMCP, pytrials, and pandas. You can install them using pip install FastMCP pytrials pandas.

Is the ClinicalTrials MCP Server free to use?

The ClinicalTrials MCP Server is licensed under the MIT License, which is a permissive open-source license.

What is UBOS, and how does it relate to the ClinicalTrials MCP Server?

UBOS is a full-stack AI Agent Development Platform. The ClinicalTrials MCP Server can be integrated with UBOS to orchestrate AI Agents, connect them with enterprise data, build custom AI Agents, and create Multi-Agent Systems for more advanced healthcare and research applications.