xiaoyibao-clinical-trials
a MCP server developed by [xiao-x-bao community](https://info.xiao-x-bao.com.cn) for clinical trials from ClinicalTrials.gov API v2. Supports searching by keywords, disease, location with intelligent defaults (recruiting trials from past 3 months
claude mcp add --transport stdio pancrepal-xiaoyibao-xiaoyibao-clinical-trials-mcp-server npx -y xiaoyibao-clinical-trials
How to use
This MCP server provides an interface for querying ClinicalTrials.gov via an intelligent search. It exposes tools to search for trials with smart defaults, fetch full trial details, and locate trials by geographic location. The available tools are: 1) search_clinical_trials — performs a keyword/condition/location-based search with defaults aimed at finding currently recruiting trials within the past three months; 2) get_trial_details — retrieves comprehensive trial information such as PI, locations, contacts, eligibility, and outcomes; 3) search_by_location — locates trials near given geographic coordinates with adjustable radius and optional filters. To use, connect your MCP client to the server and call these tools with the appropriate parameters. The server handles bilingual queries and returns results in a structured JSON format suitable for downstream processing.
How to install
Prerequisites:
- Node.js (recommended v14+ or v16+) and npm installed on your system
- Access to the internet to fetch the MCP server package
Installation options:
- Run without installation (recommended):
npx -y xiaoyibao-clinical-trials
This uses npx to execute the server on demand without a local install.
- Global installation (optional):
npm install -g xiaoyibao-clinical-trials
Then run:
xiaoyibao-clinical-trials
- Local development (if you want to pin a specific version):
mkdir my-mcp-server && cd my-mcp-server
npm init -y
npm install xiaoyibao-clinical-trials@latest
Then run the server via Node (if the package exposes a CLI) or as documented by the package.
Note: The README indicates the primary usage is via npx for zero-install convenience.
Additional notes
Tips and caveats:
- Default behavior for search_clinical_trials targets RECRUITING trials from the past 3 months with up to 30 most relevant results.
- You can override defaults by providing parameters like keywords, condition, country, or months.
- The tools support bilingual queries (English and Chinese) and return structured JSON suitable for programmatic consumption.
- If you encounter network or API rate limits, consider fetching trial details in batches and respecting API quotas.
- Ensure you pass required parameters (e.g., nctId for get_trial_details) to avoid errors.
- The npm package name for this server is xiaoyibao-clinical-trials; use it in npm-based workflows or when configuring MCP clients.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.