cardiovascular-disease-mcp
MCP server for calculating a patient's 10-year ASCVD risk using the Pooled Cohort Equations. Enables LLMs to compute cardiovascular risk scores based on patient demographics and clinical factors.
README
Cardiovascular Disease MCP
An open source repository containing a CVD risk model predictor and an external MCP server for use in Darena Health (MeldRx)
CVD Risk Model
Utilizes the risk model from Oracle Health's ascvd-risk-calculator which is based off of the Pooled Cohort Equations and lifetime risk prediction tools. This calculator follows the 2013 ACC/AHA Guideline on the Treatment of Blood Cholesterol to Reduce Atherosclerotic Cardiovascular Risk in Adults.
This tool is intended for those with an assumed LDL - Cholesterol < 190 mg/dL, and the following are a number of factors required to calculate an estimated ASCVD risk:
- Sex
- Age
- Race
- Total Cholesterol
- HDL - Cholesterol
- Systolic Blood Pressure
- Diabetes status
- Current Smoking status
- Treatment for Hypertension status
The risk scores calculated by this tool and any recommendations provided are intended to inform, and should not supersede any findings or opinions by a care provider.
The file associated with the model calculation is located in mcp-tools/calculate-cvd-risk-tool
10-year ASCVD Risk
The 10-year risk estimate provided by this application is primarily applicable towards African-American and non-Hispanic white men and women between the ages of 40 and 79 years. Other ethnic groups will have their score calculated with the same equation for non-Hispanic white men and women, though the score estimated may underestimate or overestimate the risk for these persons.
MCP server
This custom MCP server is based off of Darena Health's default Community MCP Repository
File structure
- MCP tools (context functions for LLM): /mcp-tools
- FHIR server wrapper for context: fhir-utilities.ts
Running Locally
- Install NPM and install/update Node
- Run
npm installto install all dependencies onto the project - Run
npm startto start the server on port 5000 of localhost
<details> <summary>Running on Docker</summary>
Running on Docker
-
Install and open Docker Desktop
-
In terminal, run this to create a docker image and run the container
docker-compose up --build
</details>
Creating a web-facing API endpoint
For local development, use ngrok for creating a quick endpoint for your local MCP server.
-
Install ngrok and create an auth token by making an account
-
In your terminal, run
ngrok http 5000 -
Copy the ngrok forwarded URL (highlighted below)

-
In MeldRx, navigate to your
workspace -> AI -> MCP Serversand clickAdd External MCP Server -
Input the fields as outlined below and click
TestandSave
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.