- LOW
- INTERMEDIATE
- HIGH
- HUMAN
Short answer
How can I use my AI to stratify patient mortality risk?
Your agent uses the GRACE Score Calculator to map clinical inputs to specific risk categories and mortality probabilities. You get a clear breakdown of risk levels below.
Risk outcomes.
Where risk levels land.
The AI categorizes patients based on the calculated GRACE score.
LOW
Low risk tier
The AI identifies patients with minimal mortality probability. You get a classification for standard monitoring.
INTERMEDIATE
Moderate risk tier
The AI flags patients in the middle risk bracket. This signals a need for closer observation.
HIGH
High risk tier
The AI identifies patients with significant mortality probability. This triggers immediate clinical attention.
HUMAN
Clinical review required
The AI provides the score and category, but you must make the final medical determination. It doesn't replace your judgment.
The workflow
What your AI does when clinical data arrives.
The agent handles the math and the mapping so you can focus on the patient.
Calculate the score
The AI takes your patient's clinical parameters and runs the GRACE algorithm.
get_risk_categoryAssign risk category
The agent maps the resulting score to a specific risk level.
get_risk_categoryDetermine probability
The AI pulls the corresponding mortality probability for that specific risk tier.
get_risk_categoryPresent findings
The agent delivers the risk tier and probability directly in your chat interface.
get_risk_category
Try it
Copy these to start.
Use these prompts to trigger the risk stratification.
Starting points
Replace the bracketed text with your actual patient data.
GRACE Score Calculator API Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_HYeTtzURqysRc2sZekym5U5t205c2jbn6Omm33VQ/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — GRACE Score Calculator API capabilities are ready to use.
{
"mcpServers": {
"grace-score-calculator-mcp": {
"url": "https://edge.vinkius.com/vk_preview_HYeTtzURqysRc2sZekym5U5t205c2jbn6Omm33VQ/mcp"
}
}
}Calculate the GRACE score for a patient with [age], [systolic BP], and [heart rate].
What is the mortality risk category for a GRACE score of [score]?
Based on these clinical values [list values], what is the patient's risk tier?
Run a risk stratification for a patient with [list clinical data].
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect GRACE Score Calculator once, then ask.
One link connects the MCP to your client. Your credentials stay encrypted, and you can find the full tool list on the Connector page.
Connect GRACE Score Calculator to your AIFAQ
How this task behaves.
- 01
Does the AI make the final medical diagnosis?
No. The AI only calculates the score and provides the risk category. You must interpret these results clinically.
- 02
Can the AI change the patient's treatment plan?
No. The tool is for risk stratification only. It doesn't have the capability to modify medical records or orders.
- 03
What data do I need to provide?
You need to provide the specific clinical variables required by the GRACE algorithm, such as age, heart rate, and blood pressure.
- 04
Will the AI save these scores to my EHR?
No. This MCP only performs calculations and returns data to your chat interface.
- 05
How accurate is the risk category?
The accuracy depends on the clinical data you provide. The AI strictly follows the GRACE scoring logic.
More questions about GRACE Score Calculator? The Connector page answers them. See everything the GRACE Score Calculator Connector can do
Connect GRACE Score Calculator API to Claude, Cursor, ChatGPT & more
