How to Use the Epic Fhir MCP in LangChain

Q: How do I configure Epic Fhir tools inside my LangChain agent?

Install langchain-mcp-adapters and initialize the MultiServerMCPClient with your server URL. Get the tools via client.gettools() and pass them directly to your createagent function.

Q: Can I trace Epic Fhir tool payloads in LangChain using LangSmith?

Yes, every call to tools like listobservations or listmedications automatically registers in your LangSmith traces. You get full visibility into the exact JSON payloads, latencies, and token counts.

Q: How does LangChain handle complex patient search inputs with Epic Fhir?

Your agent uses searchpatients to find matching demographics, then feeds the resulting ID into subsequent chain steps. The ReAct loop determines if it needs to call getpatient to resolve ambiguities.

Q: What is the best way to maintain session state across clinical queries?

LangChain agents are stateless by default, but you can use client.session() to preserve context. This keeps patient details handy across consecutive queries without repeating the initial authentication handshake on the stateless MCP client.

Q: How is patient health information protected during Epic Fhir queries?

The server processes highly sensitive data like listallergies and listimmunizations in an ephemeral, zero-trust V8 sandbox. No clinical records are cached or stored on Vinkius servers, ensuring complete compliance with your institution's data governance policies.

Get patient histories directly into your LangChain chains and track every single tool call with LangSmith.

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 LangChain

Create your Vinkius account to connect Epic Fhir to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step clinical reasoning chains

This MCP Server exposes tools like `get_patient` and `list_conditions` directly to your LangChain ReAct agents. You construct a pipeline where the output of one tool call immediately feeds the next, letting your agent fetch a patient's identity and then immediately query their specific medical history. The agent decides which tool to run based on real-time data instead of relying on hardcoded paths. You write the prompt, pass the tools, and let your LangGraph setup handle the state transitions.

Trace every FHIR query with LangSmith

Running `list_observations` and `list_diagnostic_reports` in production requires absolute visibility to prevent hallucinated clinical details. LangChain integrates directly with LangSmith to trace the exact input parameters and raw JSON payloads of every single tool execution. You see exactly when the agent calls `list_medications` and how it structures the query. This telemetry lets you debug latency bottlenecks and verify token usage before deploying to clinical staff.

Aggregate multiple MCP servers in LangChain

Using the `search_patients` tool alongside the `MultiServerMCPClient` lets you aggregate multiple sources. Your agent queries Epic, pulls the record, and then queries a local vector store to find matching clinical trial protocols. You manage these connections through a single stateless client setup. Call `client.session()` when you need to maintain persistent context across complex multi-turn medical chat sessions.

Setup guide

Set up Epic Fhir MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Epic Fhir tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "epic-fhir-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Epic Fhir transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and initialize the `MultiServerMCPClient` with your server URL. Get the tools via `client.get_tools()` and pass them directly to your `create_agent` function.

Yes, every call to tools like `list_observations` or `list_medications` automatically registers in your LangSmith traces. You get full visibility into the exact JSON payloads, latencies, and token counts.

Your agent uses `search_patients` to find matching demographics, then feeds the resulting ID into subsequent chain steps. The ReAct loop determines if it needs to call `get_patient` to resolve ambiguities.

LangChain agents are stateless by default, but you can use `client.session()` to preserve context. This keeps patient details handy across consecutive queries without repeating the initial authentication handshake on the stateless MCP client.

The server processes highly sensitive data like `list_allergies` and `list_immunizations` in an ephemeral, zero-trust V8 sandbox. No clinical records are cached or stored on Vinkius servers, ensuring complete compliance with your institution's data governance policies.

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