Healthcare MCP Server

Healthcare MCP Server

A Gradio MCP server that lets an assistant look up FDA drug information, PubMed papers and Health.gov topics. For developers and researchers who need medical reference lookups.

Made by Agents-MCP-Hackathon on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Healthcare MCP Server is a Gradio version of an existing healthcare MCP server. It connects an AI assistant to medical data through three lookups: drug information from the FDA database, medical papers from PubMed, and health topics from Health.gov. The Space carries an MCP tag.

Who it suits: Developers building assistants that need medical reference lookups, and researchers who want an AI tool to search drug records and literature.

Industry | Who uses it | How they use it | Example
Healthcare software | Developers | Give an assistant access to drug and health references | Looking up a drug's FDA record from an assistant
Research | Medical researchers | Search medical literature from a chat | Finding PubMed papers on a topic
Education | Health students | Find evidence-based health information | Reading a health topic summary

You can skip it if you need personal medical advice, since this is a set of reference lookups.

Where to use it:

• A web browser, on the Space's own page at Hugging Face
• An MCP client, since the Space carries an MCP tag, though the source gives no client setup
• A copy on your own computer, using Python on Windows, macOS or Linux

Use case | Who | What they get back
Check a drug | Developers and researchers | Drug information from the FDA database
Search literature | Researchers | Papers from PubMed's database
Look up a health topic | Students | Evidence-based information from Health.gov

How to set it up:

• A browser, if you only use the Space online
• Python and pip, if you run a copy yourself
• An internet connection, since the lookups reach outside data sources

1. Open the Space's page on Hugging Face to use it online. Nothing needs installing.
2. For a local copy, install the huggingface_hub package and download the Space's files.
3. Move into the new folder, then install Gradio and the packages in requirements.txt.
4. Start the server with python and its main file, gradio_server.py.

pip install -U huggingface_hub
hf download Agents-MCP-Hackathon/healthcare-mcp-public --repo-type space --local-dir healthcare-mcp-public
cd healthcare-mcp-public
pip install gradio==5.33.0
pip install -r requirements.txt

How to use it: Open the Space's page and choose a lookup: drug information, PubMed research or health topics. Enter what you want to find and read what comes back. On your own computer, start the server first and open the page it serves.

python gradio_server.py

Tool | What it does
FDA Drug Information | Searches and retrieves drug information from the FDA database
PubMed Research | Searches medical papers in PubMed
Health Topics | Fetches evidence-based health information from Health.gov

Example: You ask the FDA Drug Information lookup about a drug by name. The server returns the drug information it finds in the FDA database, which you or your assistant can then read.

For newcomers and experts: If you are new to this, MCP is a way for an AI assistant to call outside tools. Open the Space and try one lookup by hand first.

For experts, this is a Gradio adaptation of an earlier healthcare MCP server, so the tools are served from gradio_server.py with the lookup code in the src folder. It runs on Hugging Face's basic CPU hardware, and the source names no key.

Choose a lookup
Enter a drug, topic or search
The server queries the data source
Results come back to you or your assistant

Good to know:

• Built with Gradio 5.33.0, and the main file is gradio_server.py
• License: apache-2
• Cost to run: none named
• Data it reaches: the FDA drug database, PubMed and Health.gov
• Not for: personal medical decisions, since it only retrieves reference information

On Hugging Face, 13 November 2026

• Likes: 24
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Agents-MCP-Hackathon/healthcare-mcp-public
• Files: https://huggingface.co/spaces/Agents-MCP-Hackathon/healthcare-mcp-public/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.