How to Use the CHA₂DS₂-VASc & HAS-BLED Calculator MCP in Google ADK

Q: Does the MCP Server support complex recommendation logic?

It does. After calculating both stroke risk via querycha2ds2vascscore and bleeding risk with calculatehasbledscore, you can use a third tool to get combined clinical recommendations.

Enterprise Risk Scoring with Google ADK. Actionable insights for your BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CHA₂DS₂-VASc & HAS-BLED Calculator MCP to Google ADK

Create your Vinkius account to connect CHA₂DS₂-VASc & HAS-BLED Calculator to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup CHA₂DS₂-VASc & HAS-BLED Calculator with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scoring Against Enterprise Data

Your agent can assess stroke risk by calling `query_cha2ds2_vasc_score`. This is perfect when you pull patient records from BigQuery first. The MCP Server takes the structured data and returns a definitive CHA₂DS₂-VASc score. This capability lets your agents act directly on data already resident in Google Cloud, keeping everything within the enterprise ecosystem.

Holistic Risk Recommendation Generation

When you run `get_risk_recommendations`, the agent gets more than just two numbers. It receives a full set of clinical suggestions that balance stroke prevention against bleeding danger. This is crucial for high-stakes decision support. The MCP Server manages this complex logic, ensuring your long context reasoning can incorporate both risk metrics seamlessly.

Accurate Bleeding Risk Calculation

Need to know the immediate bleeding danger? The `calculate_hasbled_score` tool calculates the HAS-BLED score for any given patient. It uses established clinical guidelines, giving you a clear risk assessment number. Because of its native integration with Google Cloud, this MCP Server works well when your agents need to perform quick calculations before writing results back to BigQuery.

Setup guide

Set up CHA₂DS₂-VASc & HAS-BLED Calculator MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with CHA₂DS₂-VASc & HAS-BLED Calculator tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="CHA₂DS₂-VASc & HAS-BLED Calculator_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CHA₂DS₂-VASc & HAS-BLED Calculator tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect CHA₂DS₂-VASc & HAS-BLED Calculator now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about CHA₂DS₂-VASc & HAS-BLED Calculator MCP in Google ADK

The MCP Server acts as a reliable toolset for your LlmAgent. It accepts structured inputs from BigQuery and returns validated, ready-to-use risk scores, making the calculation part of your overall data pipeline.

Yes. Since it supports Stdio and HTTP transports, you can feed batches of patient records into the tools for scoring. The agent will process them sequentially or in parallel.

All credential passing happens through a zero-trust proxy. The user's keys are used only in transit and never stored on any disk, keeping your data compliant within Google Cloud.

It does. After calculating both stroke risk via `query_cha2ds2_vasc_score` and bleeding risk with `calculate_hasbled_score`, you can use a third tool to get combined clinical recommendations.

This MCP Server primarily handles structured patient data, including age, history of stroke (C), and various comorbidity flags necessary for calculating both the CHA₂DS₂-VASc and HAS-BLED scores.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript