How to Use the FDA (openFDA) MCP in Pydantic AI

Q: Can I use Pydantic AI to monitor food recalls using the FDA (openFDA) server?

Yes, your agent can call searchfoodenforcement and searchfoodadverseevents. The framework validates the recall descriptions and distribution patterns against your defined Python types.

Q: How do I monitor API usage to prevent rate limits?

You query getusage to inspect your current rate limits. This returns structured usage metrics that you can validate and use to throttle agent requests programmatically.

Run type-safe public health agents that validate FDA (openFDA) data at runtime using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FDA (openFDA) MCP to Pydantic AI

Create your Vinkius account to connect FDA (openFDA) 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 FDA (openFDA) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe drug approvals via Pydantic AI

This MCP Server provides direct access to the national registry using `search_drug_approvals` to verify brand names and generic alternatives. Pydantic AI enforces strict runtime validation on the returned JSON, ensuring your agent never processes malformed regulatory data. If the API schema changes or returns unexpected null values, the framework raises a validation error immediately. This prevents silent failures in your clinical decision support systems, keeping your data pipeline predictable and secure.

Strict adverse event validation

Your agent uses `search_drug_adverse_events` to monitor post-market safety signals and patient reports. Pydantic AI parses these complex, nested payloads into strongly-typed Python models, giving your code autocomplete and type-checking out of the box. You map the outputs of `search_ndc` directly to your internal database schemas. This setup guarantees that every drug code, label update, and recall notice matches your application's expected format before it ever hits your database.

Bulletproof supply chain monitoring

The MCP Server exposes `get_drug_shortages` and `search_drug_enforcement` to track active market disruptions and product recalls. Your agent queries these tools to flag supply chain issues, validating every shortage status against strict Pydantic schemas. By using the unified MCPToolset class, you connect Pydantic AI to the external server over secure HTTP. This keeps your agent code model-agnostic, allowing you to swap LLMs while maintaining identical validation rules for your public health data.

Setup guide

Set up FDA (openFDA) 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": {
        "fda-openfda-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent FDA (openFDA) 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 FDA (openFDA). 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 FDA (openFDA) 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 FDA (openFDA) MCP in Pydantic AI

Create an MCPToolset pointing to your Vinkius HTTP endpoint and pass it to your agent's toolsets list. This exposes tools like `search_drug_labels` to your agent with automatic runtime validation.

The framework raises a validation error at runtime rather than letting your agent hallucinate. This is crucial when parsing complex schemas from `search_drug_adverse_events`, where missing fields could otherwise corrupt downstream clinical logic.

Yes, your agent can call `search_food_enforcement` and `search_food_adverse_events`. The framework validates the recall descriptions and distribution patterns against your defined Python types.

You query `get_usage` to inspect your current rate limits. This returns structured usage metrics that you can validate and use to throttle agent requests programmatically.

This MCP Server strictly processes public FDA data, including drug ingredients, classifications, and shortage statuses, meaning no private patient records are ever accessed. The connection runs through Vinkius's secure, ephemeral sandbox, keeping your infrastructure isolated and compliant.

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