How to Use the Epic Fhir MCP in CrewAI

Q: How do I give my CrewAI agents access to the Epic Fhir tools?

You pass the MCP server URL into the mcps parameter when defining your Agent in CrewAI. You can also use toolfilter to assign specific tools, like giving one agent only searchpatients and another the full suite of list tools.

Deploy autonomous agent crews on Epic data with CrewAI. Assign roles for patient search, data analysis, and clinical summarization.

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 CrewAI

Create your Vinkius account to connect Epic Fhir to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a Clinical Research Crew

This server gives your CrewAI agents the tools to work together on patient data. Assign one agent the role of 'Patient Finder' and give it the `search_patients` tool. A second 'Data Analyst' agent can then take the patient ID and use `list_conditions` and `list_medications` to pull the history. A final 'Summarizer' agent can take the structured data from the analyst and write a clean summary. CrewAI's shared memory means the agents pass context seamlessly. You're not just running a script; you're coordinating a team.

Monitor Patient Data with Specialized Agents

Create a 'Vitals Monitor' agent that periodically uses the `list_observations` tool to check for new `vital-signs` data. If it spots an anomaly, it can pass the patient ID to an 'Escalation' agent. The 'Escalation' agent could then use `get_patient` to get contact info and `list_appointments` to see the primary provider, then formulate a notification. This is how you build an autonomous monitoring system using this MCP server and CrewAI.

Delegate Data Pulls with a CrewAI MCP Server

Stop writing monolithic data-fetching scripts. With CrewAI, you can have one agent dedicated to pulling `list_diagnostic_reports` and another focused on `list_immunizations`. You can filter which tools each agent in your crew gets, enforcing separation of concerns. This approach makes your system cleaner and easier to debug. If the immunization data is wrong, you know exactly which agent—and which tool call—is the source of the problem. It's a smarter way to work with complex data sources like the Epic FHIR API.

Setup guide

Set up Epic Fhir MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Epic Fhir tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Epic Fhir Analyst",
    goal="Access and analyze Epic Fhir data via MCP.",
    backstory="Expert analyst with direct Epic Fhir access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Epic Fhir transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Epic Fhir Analyst",
        goal="Access and analyze Epic Fhir data via MCP.",
        backstory="Expert analyst with direct Epic Fhir access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Epic Fhir transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass the MCP server URL into the `mcps` parameter when defining your Agent in CrewAI. You can also use `tool_filter` to assign specific tools, like giving one agent only `search_patients` and another the full suite of `list_` tools.

Absolutely, that's the ideal use case. For example, have a 'Researcher' agent use `search_patients` and a 'Compiler' agent use `list_conditions` and `list_medications` to create a patient brief. CrewAI manages the handoff between them.

Simplicity and security. The MCP server handles authentication and standardizes the tool definitions for CrewAI. You don't have to build custom LangChain tools or manage OAuth tokens; you just give the crew a URL.

Yes. The tools are stateless and can be called by any agent at any time. This fits perfectly with both simple sequential workflows and more complex hierarchical crews where a manager agent delegates tasks to subordinates.

Each tool call is an independent, isolated transaction through the Vinkius platform. Even with multiple agents, the server only fetches the specific data requested by a tool like `list_allergies` or `list_encounters` for that one operation. No patient health information is ever stored by the server itself.

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