fda_openfda.safety.drug_recalls
Search FDA drug recall enforcement records — 17,000+ drug recall actions. Returns recall classification (Class I=serious/Class II/Class III), status (Ongoing/Terminated/Completed), reason for recall, recalling firm, product description, distribution pattern, and recall initiation date. Filter usi...
This record as markdown: /tools/io-github-whiteknightonhorse-apibase/fda-openfda.safety.drug-recalls.md
What fda_openfda.safety.drug_recalls does on Apibase
AI agents call fda_openfda.safety.drug_recalls to retrieve information from Apibase without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
skip | integer | — | Number of records to skip for pagination (default 0). |
limit | integer | — | Number of records to return (1–99, default 10). |
search | string | — | OpenFDA search expression using Lucene syntax. Single field: brand_name:"tylenol" or classification:"Class I". Combined: generic_name:"ibuprofen"+AND+dosage_for |
Parameters from the server's own tool schema.
Why fda_openfda.safety.drug_recalls is rated Low
Retrieves and queries public FDA drug recall data without side effects or modifications.
From the tool's definition Search FDA drug recall enforcement records, filter using Lucene syntax
Attacks that exploit this kind of access
The rule that runs fda_openfda.safety.drug_recalls safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Apibase, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fda_openfda.safety.drug_recalls, this is the rule to start with:
fda_openfda.safety.drug_recalls is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Apibase, apply this rule, and every fda_openfda.safety.drug_recalls call is checked against it from then on.
Questions about fda_openfda.safety.drug_recalls
Search FDA drug recall enforcement records — 17,000+ drug recall actions. Returns recall classification (Class I=serious/Class II/Class III), status (Ongoing/Terminated/Completed), reason for recall, recalling firm, product description, distribution pattern, and recall initiation date. Filter using Lucene syntax: recalling_firm:"Pfizer" or classification:"Class I". Distinct from device recalls (openfda_devices.recalls) and food recalls (health.food_enforcement) — this covers drug products only. Source: FDA drug enforcement database, US public domain. It is categorised as a Read tool in the Apibase MCP Server, which means it retrieves data without modifying state.
fda_openfda.safety.drug_recalls accepts 3 parameters: skip, limit, search. The full parameter table on this page comes from the server's own tool schema.
Register the Apibase MCP server in PolicyLayer and add a rule for fda_openfda.safety.drug_recalls: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Apibase. Nothing to install.
fda_openfda.safety.drug_recalls is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fda_openfda.safety.drug_recalls rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for fda_openfda.safety.drug_recalls. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
fda_openfda.safety.drug_recalls is provided by the Apibase MCP server (apibase-mcp-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Apibase, and thousands of servers like it.
This server
Across the catalogue