openFDA MCP. Cross-reference drug safety, food recalls, and device failures.
openFDA: Access comprehensive U.S. public health records, including drug adverse events, food recalls, and medical device safety reports directly through your AI client. This MCP lets you construct complex queries using real-world data from the FDA databases.
Claude 
ChatGPT 
Cursor 
Gemini 
Windsurf 
VS Code 
JetBrains 
Vercel Give Claude and any AI agent real-world access
Query millions of patient reports detailing documented side effects, medication errors, or product quality complaints.
Search historical and current FDA enforcement reports for pathogens like Salmonella or Listeria.
Find records of malfunctions, injuries, or deaths associated with specific medical hardware.
Run multi-variable analytical research by inputting raw query syntax across all three databases.
Ask an AI about this
Waiting for input…
What AI agents can do with openFDA: 3 Tools for Regulatory Data
These tools let you programmatically search three distinct U.S. public health databases to correlate adverse events, recalls, and device failures.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using openFDA MCPQuery Drug Events
Searches the Drug Adverse Events database for reports of side effects, medication errors, or product quality complaints using Lucene syntax.
Query Food Recalls
Finds active and historical foodborne illness outbreaks and FDA enforcement reports...
Query Medical Devices
Searches the Medical Device Adverse Events database for records of malfunctions...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The openFDA integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on each call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with openFDA, then connect any of our 5,200+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,200+ others, all in one place
- Add new capabilities to your AI anytime you want
- Connections are secured and governed automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog weekly
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by 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.
VINKIUS CLOUD
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on each call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Gathering Safety Data Used To Be a Database Nightmare
Before connecting openFDA to your agent, you had to manage three separate login portals. You'd run reports on drug adverse events in one place, then switch over to check for food recalls related to Salmonella in another. If you needed to correlate a medication failure with a device malfunction, you were copy-pasting criteria between three different spreadsheet tabs.
Now, your agent handles the complexity. By using this MCP through Vinkius, you define the scope of the problem—say, 'all adverse events related to pacemakers and specific drugs'—and get one cohesive data pull from all regulatory sources. You spend time analyzing insights, not managing logins.
Querying Public Health Records with openFDA
The manual steps that disappear are the repetitive searches for specific pathogens across state lines and the tedious process of cross-referencing device names against known adverse event dates. You don't have to switch between query_food_recalls and query_medical_devices just to build a timeline.
What’s different now is speed and scope. Your agent doesn't just search; it constructs complex, multi-variable queries across the entire U.S. regulatory record instantly.
What openFDA MCP does for your AI
You're dealing with critical public health information that lives across three massive regulatory datasets: drugs, food items, and medical devices. Instead of manually logging into multiple government websites and wrestling with complicated API key setups, this MCP lets your agent query all three areas in one go. You can ask highly specific questions—for example, finding every reported adverse event linked to Ibuprofen and tracking active Salmonella recalls in California—using raw Lucene syntax.
The result is structured data pulled directly into your workflow. It’s a massive time-saver for anyone doing deep research or compliance checks. Because Vinkius hosts this MCP, you connect once from any compatible client and gain access to all these critical public health records.
019d75e9-50a9-7053-bf2e-09a365f66fea 
How to set up openFDA MCP
The bottom line is that your agent pulls highly technical, real-time regulatory data without needing dozens of API keys or manual web scraping.
You define the exact parameters for your search, specifying criteria like drug names, adverse reactions, or geographical locations.
Your AI agent uses the MCP to translate those parameters into a complex query understood by the FDA databases.
The system returns structured public health records, allowing you to analyze trends and specific incidents immediately.
Who uses openFDA MCP
This MCP is for the compliance officer who can't afford to miss a single safety report, and the researcher drowning in raw public health documentation. If your job requires deep data correlation between drug usage, food supply chains, and medical hardware failures, this is essential.
Runs queries to check for links between specific medications and newly reported adverse events across millions of records.
Tracks outbreaks, searching the openFDA Food Enforcement database for pathogens like Salmonella or Listeria in specific regions.
Validates company product safety by checking medical device records and ensuring compliance with FDA reporting standards.
Benefits of connecting openFDA MCP
Instead of sifting through scattered government PDFs, you can query all three databases—drug events, food recalls, and medical devices—in a single command. This saves hours of manual data aggregation.
The openFDA MCP lets your agent use raw Lucene syntax for maximum control. You aren't limited to predefined search fields; you define the exact variables needed for analysis.
You can rapidly check medication safety by using query_drug_events, finding adverse event patterns related to specific drugs or reactions across millions of records.
Compliance checks become simple: Use query_food_recalls to track if a pathogen like Salmonella was reported in a specific state and what the recall status is.
Monitor hardware integrity with query_medical_devices. This lets you check for malfunctions tied to generic device names or date ranges, which is crucial for risk assessment.
openFDA MCP use cases
Investigating a new drug side effect
A researcher needs to know if Ibuprofen has any reported links to insomnia. They ask their agent to run a query using the 'query_drug_events' tool, getting immediate confirmation of multiple adverse event records without leaving their workspace.
Auditing a food supply chain breach
A public safety team suspects a contaminated product. They use 'query_food_recalls' to track all Salmonella outbreaks in California, allowing them to pinpoint the exact source and recall status immediately.
Analyzing device failure trends
A manufacturer needs to know about potential issues with pacemakers. They run 'query_medical_devices', filtering by malfunction event type and date range, giving them actionable data for a safety bulletin.
openFDA MCP tradeoffs
What to watch out for, and the recommended way to handle each one.
Searching only one database
Trying to determine if an adverse drug event is linked to a recalled food item. This requires checking two different systems manually.
Use the openFDA MCP to combine these searches by querying both 'query_drug_events' and 'query_food_recalls' in one workflow, correlating the data points instantly.
Using vague search terms
Asking a general question like 'Is anything wrong with drugs?' which yields thousands of unhelpful results.
Use specific tools and syntax. For example, use query_drug_events to search for patient.drug.medicinalproduct:"ASPIRIN" combined with a reaction type.
Ignoring date limitations
Running a device safety check without specifying a timeframe, resulting in an unmanageable volume of old data.
Always include specific date ranges when using query_medical_devices. Define the date_of_event:[YYYYMMDD TO YYYYMMDD] to narrow your focus.
When to use openFDA MCP
Use this MCP if your job requires cross-domain correlation of public health safety data. This is for deep dives involving drug side effects, food contamination reports, and medical hardware failures. Don't use it if you simply need general information; the depth of the available tools—like query_drug_events—requires precise knowledge (e.g., Lucene syntax) to get accurate results. Conversely, don't use this MCP for internal corporate data like HR records or sales figures; these databases are strictly public health regulatory archives.
Frequently asked questions about openFDA MCP
How do I find reports on specific medication side effects using openFDA? +
You use the 'query_drug_events' tool. You input criteria like patient.drug.medicinalproduct:"ASPIRIN" combined with the desired reaction to pull adverse event records.
Does openFDA allow me to query food recalls by state? +
Yes, you can use 'query_food_recalls' and include the state parameter (e.g., state:"CA") alongside the reason for recall to narrow your search.
What kind of data does openFDA provide on medical devices? +
The 'query_medical_devices' tool provides details on injuries, malfunctions, and deaths linked to specific device types or event dates. It tracks safety reports from the MAUDE database.
Can I combine drug and food data in openFDA? +
Yes, you can build complex queries that reference both drug events and food recalls simultaneously, allowing for highly correlated public health research.
Is the data from openFDA real-time or historical? +
The MCP accesses live regulatory databases, providing both historical records (like past outbreaks) and current, ongoing reports. Always check the database's update frequency for the absolute latest information.