openFDA
Public FDA drug labels, adverse events, drug recalls, and medical device recall data.
Tools
| Name | Description |
|---|---|
search_drug_labelsSearch public FDA structured product labels. Use targeted search terms; this endpoint does not contain patient PHI. | Search public FDA structured product labels. Use targeted search terms; this endpoint does not contain patient PHI. |
search_drug_adverse_eventsSearch public FAERS drug adverse event reports by precise openFDA query. | Search public FAERS drug adverse event reports by precise openFDA query. |
search_drug_recallsSearch FDA drug enforcement/recall reports by recall number, firm, product, classification, or date query. | Search FDA drug enforcement/recall reports by recall number, firm, product, classification, or date query. |
search_device_recallsSearch FDA medical device enforcement reports by precise openFDA query. | Search FDA medical device enforcement reports by precise openFDA query. |
Quick Start
import { WeavzClient } from '@weavz-io/sdk'
const weavz = new WeavzClient({ apiKey: 'wvz_...' })
const result = await weavz.actions.execute('openfda', 'search_drug_labels', {
workspaceId: '550e8400-e29b-41d4-a716-446655440000',
integrationAlias: 'openfda',
input: { /* ... */ },
})Related Integrations
Works well with
Frequently Asked Questions
How do I connect openFDA to my app?
openFDA does not require an external account connection. Install the SDK, add the integration to a workspace, then execute tools programmatically.
What tools does openFDA support?
openFDA supports 4 tools including Search Drug Labels, Search Drug Adverse Events, Search Drug Recalls, Search Device Recalls.
Can I use openFDA with AI agents?
Yes. Add openFDA to an MCP server in Tool Mode or Code Mode. Code Mode provides 3 meta-tools with on-demand API discovery so agents can compose stateful workflows without loading every action schema up front.
How do I connect openFDA to ChatGPT or Claude?
Open the Weavz connector setup, sign in, choose a workspace, and add openFDA as an approved app. ChatGPT, Claude, and other remote MCP clients can then call the scoped openFDA tools exposed by that workspace.
Does openFDA work with Claude Code, Cursor, Codex, and local agents?
Yes. Remote and local MCP clients can connect to a Weavz MCP endpoint for the workspace. Local coding agents can also use the Weavz CLI to inspect apps, discover actions, run approved openFDA work, and execute Code Mode workflows from a terminal.
What can I ask an AI agent to do with openFDA?
openFDA exposes 4 tools, including Search Drug Labels, Search Drug Adverse Events, Search Drug Recalls, Search Device Recalls. Use Weavz to keep credentials scoped, require approval for sensitive work, and audit what the agent did.
Can openFDA be used in stateful agent workflows?
Yes. Agents can combine openFDA tools with Filesystem, State KV, Human Gates, input partials, and other workspace integrations while keeping execution scoped to the selected workspace or end user.
What authentication does openFDA use?
openFDA does not require external authentication.
How much does the openFDA integration cost?
The openFDA integration is included on all Weavz plans including the free tier with 20,000 actions per month. No credit card required.
Connect openFDA in minutes
Get 20,000 free action executions every month. No credit card required.