How to Use the FDA (openFDA) MCP in Google ADK

Q: How do I track API limits for this server?

Your agent calls getusage to retrieve real-time rate limit data. This lets you build control loops that pause queries before hitting public API thresholds.

Equip your Gemini agents with FDA (openFDA) tools to analyze public health records directly alongside your BigQuery datasets.

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 Google ADK

Create your Vinkius account to connect FDA (openFDA) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct FDA (openFDA) queries from Google ADK

This MCP Server connects your enterprise agents directly to public health registries using `search_drug_labels` to extract prescribing information. The Google ADK feeds this raw regulatory text into Gemini's 1M+ token context window, allowing deep comparative analysis across hundreds of drug labels simultaneously. You pass the HTTP server parameters to your McpToolset to expose all 12 endpoints to your agent. This lets your system run complex queries and cross-reference the results with your existing data pipelines in Google Cloud.

Automated food safety and recall tracking

Your agent uses `search_food_enforcement` and `search_food_adverse_events` to monitor active contamination reports and consumer complaints. By pulling this data directly into your Google ADK workflow, you can trigger automated warnings when a supplier matches a recalled batch. The agent writes these safety alerts directly to BigQuery for historical tracking. This setup replaces manual web scraping with structured, authenticated API queries that keep your supply chain compliance records accurate.

Medical device classification audits

The MCP Server exposes `search_device_classification` and `search_device_enforcement` to audit medical hardware inventories. Your agent queries these tools to verify that your clinical equipment matches current FDA classifications and is free of active recall notices. Using the Google ADK, you can filter which tools are exposed to specific agents. This ensures your inventory agent only accesses hardware classifications while your clinical agents focus on patient-facing drug data.

Setup guide

Set up FDA (openFDA) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with FDA (openFDA) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="FDA (openFDA)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to FDA (openFDA) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate McpToolset with your Vinkius HTTP transport URL and pass it to your LlmAgent constructor. This exposes the tools to Gemini, allowing it to call `get_drug_shortages` during reasoning steps.

Yes, you use the optional tool names filter in the McpToolset configuration to restrict access. For example, you can limit an agent to `search_drug_labels` and block access to food recall tools.

The framework processes the structured JSON payloads returned by tools like `search_drug_adverse_events`. Gemini's long context easily digests large batches of adverse event reports, which you can then stream directly into your cloud databases.

Your agent calls `get_usage` to retrieve real-time rate limit data. This lets you build control loops that pause queries before hitting public API thresholds.

The MCP Server strictly retrieves public-domain FDA data, such as drug approvals and food recalls, and never touches patient records. All traffic is routed through an ephemeral, zero-trust sandbox that isolates your Google Cloud environment from external network threats.

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