How to Use the Epic Fhir MCP in Google ADK

Feed longitudinal patient records into Gemini using our MCP Server and the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Epic Fhir MCP to Google ADK

Create your Vinkius account to connect Epic Fhir 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 Epic Fhir with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Expose Epic Fhir tools directly to Google ADK

`list_encounters` retrieves the complete visit history of a patient, feeding structured encounter types and locations directly to Gemini. This MCP Server maps this tool into your agent's workspace with a simple initialization step. Developers pass the toolset to the LlmAgent constructor to instantly grant access to clinical data. The agent can then use `list_appointments` to coordinate upcoming visits with historical encounter contexts.

Analyze massive clinical histories in Gemini

`list_observations` extracts thousands of laboratory results, vital signs, and social history records over years of treatment. Gemini's million-token context window handles this massive volume of clinical data without requiring aggressive truncation. The model correlates these observations with diagnoses retrieved via `list_conditions`. You get deep, long-context reasoning across the entire patient chart in a single execution step.

Cross-reference EHR data with BigQuery pipelines

`list_immunizations` retrieves CVX codes, administration dates, and dose details from the EHR. The Google ADK makes it straightforward to feed this structured data into BigQuery for population health analytics. Your agent can run `list_medications` to pull active prescriptions, then compare those records against regional health datasets stored in Google Cloud. This bridges the gap between individual patient charts and enterprise data warehouses.

Setup guide

Set up Epic Fhir 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 Epic Fhir 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="Epic Fhir_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Epic Fhir 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 Epic Fhir. 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 Epic Fhir 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 Epic Fhir MCP in Google ADK

Install the Google ADK package via pip, then initialize the McpToolset with your Vinkius HTTP endpoint. This exposes all 10 FHIR tools, such as `get_patient` and `list_allergies`, directly to your Gemini agent.

Yes, the McpToolset constructor accepts an optional tool name filter. You can explicitly limit the agent to `list_diagnostic_reports` and `list_observations` while hiding sensitive administrative tools.

Yes, the toolset handles both transport protocols. For cloud deployments on Google Cloud, the streamable HTTP transport is recommended to connect your server instance securely.

The model parses the ICD-10 codes and clinical status fields returned by `list_conditions`. It then uses this structured clinical history to ground its answers, ensuring it does not guess active diagnoses.

The Vinkius sandbox acts as a secure transit layer, enforcing zero-trust boundaries around every API request. No patient records retrieved via `search_patients` or `list_medications` are cached or used for training Google's models.

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