How to Use the Epic Fhir MCP in Cursor

Q: Can I use this Epic Fhir MCP Server to test data parsing for patient immunizations in Cursor?

Absolutely. You can instruct the agent to call listimmunizations for a patient. It will return the data including CVX codes and administration dates, which you can then use to generate and test your parsing logic right inside the editor.

Q: Is the setup for Epic Fhir in Cursor project-specific?

It can be. You can create a .cursor/mcp.json file in your project's root directory to share the configuration with your team. Or, you can configure it globally in /.cursor/mcp.json for all your projects.

Inject live Epic patient data directly into your code. Build healthcare apps in Cursor with real FHIR R4 API responses.

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 Cursor

Create your Vinkius account to connect Epic Fhir to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build with Live Patient Data in Cursor

Stop mocking FHIR data. With this MCP server, Cursor's agent can call the Epic API directly. Use `search_patients` to find a real (sandboxed) patient record, then `get_patient` to pull their full demographic data. The agent doesn't just show you the data; it writes the code to handle it. Ask it to generate a function that fetches and parses a patient's profile. You get working, type-safe code that uses a real API response structure, not a guess.

Prototype Clinical Workflows

Map out an entire clinical check inside your editor. Tell the agent to find a patient, then use `list_conditions` to get their diagnoses and `list_medications` to see their prescriptions. You can build and test logic for things like medication reconciliation on the fly. This isn't just about viewing data, it's about building with it. Check for conflicts with `list_allergies` and have the agent write the code for an alert. You're not just coding—you're simulating real-world scenarios with live data, which tightens your development loop.

Integrate Lab and Encounter Data

Pull in the data that usually requires complex queries. Your agent can use `list_encounters` to get a patient's visit history or `list_diagnostic_reports` to grab the text of a radiologist's findings. This is complex data, made simple. Need to build a UI that displays lab results? Ask the agent to fetch data using `list_observations` (filtered to 'laboratory') and then generate the React component to display it. You go from an idea to a working prototype with real data in a single prompt.

Setup guide

Set up Epic Fhir MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Epic Fhir MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Epic Fhir transactions." If the MCP tools are loaded correctly, Cursor will call the Epic Fhir tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "epic-fhir-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

It connects Cursor's agent to a live Epic FHIR sandbox. Instead of using mock data, the agent calls tools like `get_patient` and `list_medications` and uses the real API responses to write your code. Your functions and types will match the actual API from day one.

Absolutely. You can instruct the agent to call `list_immunizations` for a patient. It will return the data including CVX codes and administration dates, which you can then use to generate and test your parsing logic right inside the editor.

You get access to 10 core FHIR resources. This includes patient demographics (`get_patient`), diagnoses (`list_conditions`), medications (`list_medications`), allergies (`list_allergies`), lab results (`list_observations`), and appointments (`list_appointments`).

It can be. You can create a `.cursor/mcp.json` file in your project's root directory to share the configuration with your team. Or, you can configure it globally in `~/.cursor/mcp.json` for all your projects.

The data is treated as transient. The Vinkius MCP server requests data like Diagnostic Reports or Observations from Epic's API and streams it to your Cursor client for use by the agent. Nothing is logged or stored on the server, ensuring patient data isn't persisted outside of the EHR or your local machine.

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