How to Use the Epic Fhir MCP in Pydantic AI

Q: How does Pydantic AI handle validation errors from Epic Fhir MCP tools?

If a tool like searchpatients returns data that violates your schema, the framework halts execution and raises a clear validation error. This prevents your agent from hallucinating missing demographic details or MRNs.

Q: How does the integration secure sensitive clinical observations?

All traffic containing PHI retrieved via listobservations is encrypted in transit using TLS. Vinkius operates as a zero-trust gateway, meaning no clinical data is decrypted or logged on host disks during execution.

Validate clinical payloads at runtime with Pydantic AI and our Epic Fhir MCP Server.

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 Pydantic AI

Create your Vinkius account to connect Epic Fhir to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Epic Fhir resources at runtime

`get_patient` pulls detailed demographic records, including name, DOB, and identifiers, directly from the EHR. Our MCP Server pulls detailed demographic records, and Pydantic AI validates this incoming JSON payload against strict schemas before your agent ever sees the data. If the EHR returns unexpected null fields or modified schemas, the framework raises a validation error immediately. This prevents your agent from making decisions based on malformed patient profiles.

Catch schema drift on active medications

`list_medications` fetches active prescriptions, dosages, and routes. Because medical data demands absolute accuracy, the framework ensures every field matches your defined Python models exactly. The agent uses `list_allergies` to cross-reference drug intolerances safely. By failing loudly on schema mismatches, you avoid silent data corruption in critical clinical workflows.

Query structured diagnostic reports safely

`list_diagnostic_reports` retrieves laboratory results and clinical conclusions. Pydantic AI parses these complex nested structures into typed Python objects, making it easy to pass clean data to OpenAI or Anthropic models. Your agent can then invoke `list_observations` to isolate vital signs or lab values. Because the inputs and outputs are strictly typed, you eliminate parser errors when extracting numeric clinical values.

Setup guide

Set up Epic Fhir MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "epic-fhir-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Epic Fhir tools.",
)

result = await agent.run("List recent Epic Fhir transactions")
print(result.output)

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 Pydantic AI

Use the MCPToolset class with your Vinkius HTTP endpoint to register the server. Pass this toolset directly to the Agent constructor to give your model access to tools like `list_encounters` and `list_appointments`.

Yes, the validated toolset works with any LLM provider supported by Pydantic AI. You can switch your underlying model from OpenAI to Gemini without rewriting your `list_conditions` or `list_immunizations` tool logic.

If a tool like `search_patients` returns data that violates your schema, the framework halts execution and raises a clear validation error. This prevents your agent from hallucinating missing demographic details or MRNs.

Yes, the Vinkius hosting environment supports both Streamable HTTP and SSE transports. You simply pass the appropriate connection string when initializing your MCPToolset in Python.

All traffic containing PHI retrieved via `list_observations` is encrypted in transit using TLS. Vinkius operates as a zero-trust gateway, meaning no clinical data is decrypted or logged on host disks during execution.

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