How to Use the Epic Fhir MCP in OpenAI Agents SDK

Q: How does the Epic Fhir MCP Server handle tool discovery in the OpenAI Agents SDK?

The SDK automatically discovers all 10 tools, including listallergies and listappointments, when you pass the streamable HTTP server parameter to the Agent constructor. You do not need to write manual JSON schemas for the tools.

Q: How do agent handoffs work when fetching diagnostic reports and observations?

You configure one agent to run listdiagnosticreports to find recent lab dates, then hand off the execution to a secondary agent that queries listobservations for specific vital signs. The SDK manages this transition smoothly while maintaining the patient context.

Build production-grade healthcare agents that query live hospital data via our MCP Server with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Epic Fhir to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Discover Epic Fhir tools with OpenAI Agents SDK

`search_patients` acts as your entry point, allowing your agent to locate patient records by name or MRN without manual configuration. Our MCP Server registers this endpoint alongside nine other clinical tools when the agent initializes. Once the patient is identified, the agent calls `get_patient` to extract demographic details. This direct integration eliminates manual mapping because the SDK parses the FHIR R4 payloads directly into the agent's context.

Enforce safety boundaries on clinical history

`list_conditions` retrieves ICD-10 diagnoses while the SDK's built-in guardrails block unauthorized or unsafe tool executions. You define runtime constraints that prevent the agent from writing back to the EHR or summarizing data without strict validation. When pulling active prescriptions with `list_medications`, the agent operates within a read-only transport layer. The OpenAI dashboard traces every single tool execution, giving you an auditable log of which medical records were accessed and when.

Coordinate multi-agent handoffs for lab reviews

`list_diagnostic_reports` pulls raw laboratory outcomes and diagnostic summaries from the EHR. The SDK manages handoffs between specialized agents, letting a triage agent gather data before passing it to a clinical analysis agent. These specialized agents then invoke `list_observations` to filter vital signs or laboratory results. This keeps individual agent prompts small, reducing token usage and keeping the focus on specific clinical data points.

Setup guide

Set up Epic Fhir MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Epic Fhir tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Epic Fhir tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Epic Fhir tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Epic Fhir Agent",
            instructions="You have access to Epic Fhir tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The SDK automatically discovers all 10 tools, including `list_allergies` and `list_appointments`, when you pass the streamable HTTP server parameter to the Agent constructor. You do not need to write manual JSON schemas for the tools.

Yes, you can filter the tool list during initialization or use the SDK's guardrails to restrict access. This prevents an agent from executing specific tools like `list_immunizations` or `list_encounters` if its role only requires viewing patient demographics.

Set the cacheToolsList parameter to true when configuring your streamable HTTP connection. This keeps the tool definitions cached, which cuts down on latency when your agent repeatedly queries `list_medications` or `get_patient`.

You configure one agent to run `list_diagnostic_reports` to find recent lab dates, then hand off the execution to a secondary agent that queries `list_observations` for specific vital signs. The SDK manages this transition smoothly while maintaining the patient context.

Vinkius runs the MCP Server in an ephemeral, zero-trust V8 Isolate sandbox that never stores patient data or FHIR payloads. All PHI retrieved from tools like `list_allergies` or `list_conditions` passes directly to your OpenAI pipeline over an encrypted channel, bypassing local storage entirely.

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