How to Use the FDA (openFDA) MCP in LangChain

Q: Can I monitor API limits for FDA (openFDA) queries inside a LangChain run?

Yes, you can call getusage at any point in your chain to check your remaining quota. Your agent can read this integer output and dynamically throttle its search frequency to avoid hitting public rate limits. This keeps your automated pipelines running smoothly without sudden API rejections.

Q: What is the best way to handle drug recall alerts using this MCP Server?

You can set up a LangChain agent that queries searchdrugenforcement daily to flag new recalls. The agent inspects the payload, matches affected lot numbers, and alerts your team. This automates regulatory tracking without requiring a complex custom API integration.

Build multi-step FDA data pipelines in LangChain to track drug shortages, verify recalls, and inspect clinical labels.

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 LangChain

Create your Vinkius account to connect FDA (openFDA) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain drug safety checks with LangChain agents

The `search_drug_labels` tool feeds raw FDA product labeling text straight into your active reasoning chains. LangChain maps this output directly to downstream steps, allowing your agent to parse active ingredients and flag contraindications without manual copy-pasting. You configure the sequence so that finding a substance triggers a secondary lookup instantly. This setup relies on the MultiServerMCPClient to pull live regulatory data into your LangSmith-monitored pipelines using this MCP Server. By avoiding static databases, you resolve latency issues and ensure clinical decision support systems run on current federal records. Every step registers in your traces, exposing exactly how the agent extracted the label data.

Track active recalls and shortage risks

The `get_drug_shortages` tool monitors active clinical supply disruptions and feeds status updates to your agent. When a shortage is detected, your LangChain chain automatically routes to `search_drug_enforcement` to check if a recall caused the bottleneck. This programmatic triage replaces manual searching across multiple government portals. This MCP setup relies on a single Vinkius endpoint token, which keeps your execution environment clean. Your agent evaluates the status of both tools, decides which alternative generic code to look up via `search_ndc`, and outputs a structured alternative list. You get a deterministic pipeline built on real-time regulatory endpoints.

Automate food safety and device compliance

The `search_food_enforcement` tool retrieves recall notices for contaminated shipments, letting your pipeline flag high-risk batches. Your LangChain agent receives these alerts and instantly runs `search_device_adverse_events` to cross-reference related hospital equipment issues. Combining these tools in a single run gives you a clear view of supply chain hazards. Because this MCP Server runs in an isolated sandbox, your production application stays secure while pulling live public health data. The agent decides when to stop querying based on the rate limits returned by `get_usage`. You get structured, validated JSON payloads ready for your analytical databases.

Setup guide

Set up FDA (openFDA) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes FDA (openFDA) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "fda-openfda-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent FDA (openFDA) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You use the MultiServerMCPClient to load the tools and pass them to your agent executor. The agent then calls `search_drug_labels` and feeds the output directly into `search_ndc` in a single execution loop. LangSmith traces the entire sequence so you can see the exact parameters passed between tools.

Yes, you can call `get_usage` at any point in your chain to check your remaining quota. Your agent can read this integer output and dynamically throttle its search frequency to avoid hitting public rate limits. This keeps your automated pipelines running smoothly without sudden API rejections.

Your agent uses its LLM reasoning to parse the raw text returned by `search_drug_labels` into clean JSON schemas. You define the target output structure, and the agent extracts dosage, warnings, and ingredients automatically. This bypasses the need for custom regex patterns or fragile parsing scripts.

You can set up a LangChain agent that queries `search_drug_enforcement` daily to flag new recalls. The agent inspects the payload, matches affected lot numbers, and alerts your team. This automates regulatory tracking without requiring a complex custom API integration.

All queries for drug recalls, labels, or shortages run inside an isolated, zero-trust V8 sandbox managed by Vinkius. Your search terms never persist on our servers, and we handle all API authentication tokens securely. This ensures your clinical search history and intellectual property remain completely private.

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