Stroke & Bleeding Risk MCP. Get combined anticoagulation recommendations instantly.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
The CHA₂DS₂-VASc & HAS-BLED Calculator determines stroke risk (CHA₂DS₂-VASc) and bleeding risk (HAS-BLED) for patients with atrial fibrillation. This MCP integrates established clinical guidelines, giving clinicians a single view of both thromboembolic and hemorrhagic risks.
It moves beyond simple scoring by generating definitive anticoagulant recommendations based on combined patient data.
What your AI agents can do
Calculate hasbled score
It calculates the HAS-BLED score, which measures potential bleeding risk during anticoagulant therapy.
Get risk recommendations
It generates a final clinical recommendation by analyzing both stroke and bleeding scores to guide treatment decisions.
Query cha2ds2 vasc score
It calculates the CHA₂DS₂-VASc score based on patient details, determining the risk of a stroke in atrial fibrillation.
It calculates the CHA₂DS₂-VASc score using patient demographics like age, sex, and comorbidities.
It evaluates bleeding risk by running the HAS-BLED scale against factors like blood pressure control and diuretics.
It synthesizes both calculated scores into a definitive annual stroke risk percentage and anticoagulant guidance (O or A).
It incorporates multiple chronic conditions, such as hypertension and diabetes, directly into the base risk calculation.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
CHA₂DS₂-VASc & HAS-BLED Calculator - 3 Tools
These three tools guide you through a complete risk assessment workflow: calculating stroke risk, assessing bleeding risk, and finally synthesizing both into an actionable clinical recommendation.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using CHA₂DS₂-VASc & HAS-BLED Calculator on Vinkius019ecb72calculate hasbled score
It calculates the HAS-BLED score, which measures potential bleeding risk during anticoagulant therapy.
019ecb72get risk recommendations
It generates a final clinical recommendation by analyzing both stroke and bleeding scores to guide treatment decisions.
019ecb72query cha2ds2 vasc score
It calculates the CHA₂DS₂-VASc score based on patient details, determining the risk of a stroke in atrial fibrillation.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with CHA₂DS₂-VASc & HAS-BLED Calculator, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CHA₂DS₂-VASc & HAS-BLED Calculator. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 3 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
The challenge of balancing stroke prevention and bleeding risk
Right now, figuring out anticoagulation for Atrial Fibrillation feels like a guessing game. You're constantly clicking between separate guidelines: one sheet tells you the patient's chance of stroke, and another tells you how likely they are to bleed if you start medication. You end up comparing two numbers—a risk score here, a warning flag there—and the final decision requires manual judgment that is prone to human error.
With this MCP, your agent handles the complexity. It runs the patient data against both established stroke prevention metrics and bleeding danger indicators simultaneously. Instead of just handing you raw scores, the system gives you a synthesis: actionable advice on annual risk percentage and whether anticoagulation is appropriate.
Get Risk Recommendations with get_risk_recommendations
The MCP removes the need to manually interpret what two separate scores mean together. It doesn't just show you a high CHA₂DS₂-VASc score and a moderate HAS-BLED score; it processes both through `get_risk_recommendations`.
You get an immediate, clinically guided recommendation that addresses the trade-off between preventing stroke and managing bleeding risk. That’s how efficient modern care works.
What you can do with this MCP connector
Managing Atrial Fibrillation requires balancing two opposing forces: preventing stroke versus avoiding excessive bleeding. Simply calculating scores separately leaves the clinician guessing how to weigh these risks against each other. This MCP takes a patient's full profile—their age, comorbidities, blood pressure control, and medication use—and runs it through established protocols simultaneously.
It doesn't just provide two numbers; it synthesizes those factors into actionable guidance. Your agent calculates the base stroke risk using one tool, assesses bleeding danger with another, and then combines both findings to generate a final recommendation for annual stroke risk percentage and whether anticoagulation is needed. Because this process involves multiple calculations drawing from diverse clinical data points, Vinkius's secure architecture ensures that all credentials pass through a zero-trust proxy; your keys are used only in transit and never saved on disk.
019ecb72-1dcc-7249-9738-840a30cc8d97 
How Stroke & Bleeding Risk MCP Works
- 1 You feed the agent a patient's full profile: age, sex, comorbidities (HTN, DM), blood pressure readings, and medication history.
- 2 The MCP runs the data through the first two specialized calculations to get both the stroke risk score and the bleeding risk score.
- 3 Finally, it combines these two scores using the third tool to generate a singular, definitive recommendation for anticoagulation.
The bottom line is that you stop manually cross-referencing charts; you get one integrated answer based on all established guidelines.
Who Is Stroke & Bleeding Risk MCP For?
Cardiology fellows and primary care providers who spend too much time toggling between multiple risk assessment sheets. You're the clinician tired of making a final decision based only on half the picture.
Uses this to standardize initial patient evaluations, ensuring they don't miss critical bleeding or stroke risk factors when managing stable AFib patients.
Runs the full assessment on site during follow-up visits, providing immediate, evidence-based recommendations for anticoagulation changes.
Develops protocols by running batch assessments of patient cohorts to identify systemic gaps in current care pathways.
What Changes When You Connect
- Avoid siloed thinking. Instead of just seeing a high CHA₂DS₂-VASc score, the agent uses
query_cha2ds2_vasc_scoreand then immediately balances it against bleeding risk viacalculate_hasbled_scoreto give you the full picture. - Stop guessing about guidelines. The final step, using
get_risk_recommendations, delivers a definitive annual stroke risk percentage and clear 'O' or 'A' guidance, making your protocol recommendations faster. - It handles complex data dependencies automatically. You feed the agent one set of inputs (age, HTN status, etc.), and it manages running three distinct calculations behind the scenes.
- The system doesn't just list scores; it synthesizes them. This is crucial because a high thromboembolic risk can be mitigated by accepting a higher bleeding risk—the MCP tells you how to weigh that trade-off.
- Confidence in decisions increases. Because the process mimics established clinical guidelines, your agents provide recommendations that are auditable and defensible.
Real-World Use Cases
Initial patient intake for AFib
A new patient arrives with suspected Atrial Fibrillation. The agent first runs query_cha2ds2_vasc_score to establish the baseline stroke risk. Next, it uses calculate_hasbled_score to check their current blood pressure and diuretic use. Finally, get_risk_recommendations spits out a clear recommendation for immediate next steps.
Adjusting medication after hospitalization
A patient was hospitalized and had minor GI bleeding. The clinician needs to know if they can safely maintain anticoagulation. The agent runs both query_cha2ds2_vasc_score (to confirm persistent stroke risk) and calculate_hasbled_score, allowing the final recommendation tool to weigh safety over absolute prevention.
Comparing two patients with similar symptoms
You have Patient A, who is young but has multiple comorbidities, and Patient B, who is older but healthy. The agent can run both profiles through query_cha2ds2_vasc_score and calculate_hasbled_score side-by-side to quickly pinpoint which patient's risk profile is more concerning.
Pre-procedure assessment
Before a planned cardiac procedure, the nurse needs an immediate risk summary. The agent gathers all current data points and uses get_risk_recommendations to give a rapid consensus on whether anticoagulation should be continued or temporarily paused.
The Tradeoffs
Calculating scores manually
Reading the guidelines, writing down all the patient's factors (age, HTN, DM), and then cross-referencing them against separate stroke risk charts and bleeding guides. It takes 20 minutes of paperwork.
→
Feed the agent the single patient profile once. The system handles running query_cha2ds2_vasc_score and calculate_hasbled_score, then consolidates everything with get_risk_recommendations to give you an instant, weighted answer.
Ignoring conflicting scores
Seeing a high CHA₂DS₂-VASc score but also seeing signs of recent GI bleeding. The clinician is left debating whether the risk profile warrants anticoagulation or not.
→
Use get_risk_recommendations. This tool isn't just listing scores; it’s designed to weigh the conflict, providing a final, clinically guided recommendation that accounts for both risks simultaneously.
Using only one score
Only running calculate_hasbled_score because bleeding is currently the biggest concern. You miss the fact that the patient’s underlying stroke risk was actually higher than you thought.
→ Always run the full suite of tools together. Let the agent use both the CHA₂DS₂-VASc score and the HAS-BLED score to ensure no critical piece of data is overlooked.
When It Fits, When It Doesn't
Use this MCP if you need a single, synthesized recommendation that explicitly weighs two major, opposing clinical risks (stroke vs. bleeding). This is mandatory when managing AFib patients where the risk profile is ambiguous or complex. Don't use it if you only need to check one score—for instance, if your primary concern is only monitoring blood pressure control, a dedicated BP tool is fine. But if you need to know what anticoagulant therapy is best given the patient’s whole picture, this MCP is necessary because it connects query_cha2ds2_vasc_score and calculate_hasbled_score before giving the final answer via get_risk_recommendations. Never rely on only one score; always use the combined assessment.
Common Questions About Stroke & Bleeding Risk MCP
How does the CHA₂DS₂-VASc & HAS-BLED Calculator use `query_cha2ds2_vasc_score`? +
The MCP uses this tool to calculate the base risk by assessing factors like age, sex, and comorbidities (HTN, DM). This establishes the patient's initial likelihood of having a stroke.
What specific data does `calculate_hasbled_score` require? +
This tool primarily requires information about blood pressure control and whether the patient is on diuretic medications to accurately assess bleeding risk during treatment.
Can I use this MCP if the patient has multiple conditions? +
Yes. The system is designed for integrated care, allowing you to input all comorbidities (like HTN and DM) into the initial data set, ensuring the full risk profile is considered.
What does `get_risk_recommendations` provide? +
It synthesizes the two calculated scores, giving you a definitive annual stroke risk percentage (based on ESC 2020 criteria) and whether anticoagulation is recommended ('O' or 'A').
When running both `query_cha2ds2_vasc_score` and `calculate_hasbled_score`, how does Vinkius secure patient data? +
Your credentials pass through a zero-trust proxy, meaning your keys are used in transit but never stored on disk. Every single tool call generates a cryptographically signed audit trail for full accountability.
If an error occurs during `query_cha2ds2_vasc_score`, how does the system prevent bad data from reaching `get_risk_recommendations`? +
The MCP is designed to handle failures gracefully. If any tool fails, it reports exactly which function caused the issue and prevents incomplete or invalid scores from being used in the final recommendation step.
What AI clients can access this MCP for calculating scores using `calculate_hasbled_score`? +
You connect once through any MCP-compatible client, like Claude or Cursor. That single connection gives your agent access to every tool in the Vinkius catalog, not just this risk assessment.
How does the platform optimize calls when I run all three tools, including `query_cha2ds2_vasc_score`? +
The MCP includes native token optimization built into every call. This cuts down token consumption by up to 60% compared to running these calculations without optimization.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
