fda_recalls
FDA recalls (openFDA): drug, device and food enforcement reports (class, status, firm, reason, distribution, lots) plus the device recall database (root cause). Filter by firm, product, class, status, state, dates; count by any field. Newest first. Price: $0.01 USDC per successful call (x402, Sol...
This record as markdown: /tools/com-it-scorptech-x402/fda-recalls.md
What fda_recalls does on ScorpTech x402 API
AI agents call fda_recalls to retrieve information from ScorpTech x402 API 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 |
|---|---|---|---|
to | string | — | on/before YYYY-MM-DD |
firm | string | — | recalling firm |
from | string | — | on/after YYYY-MM-DD |
skip | integer | — | offset 0-25000 |
sort | string | — | field:asc|desc (default newest) |
count | string | — | count by field, e.g. recalling_firm.exact |
limit | integer | — | 1-100 (default 10); count 1-1000 |
state | string | — | US state of the firm (2 letters) |
reason | string | — | reason-for-recall phrase |
search | string | — | raw openFDA search, ANDed |
source | string | — | enforcement (default) or recall (device only) |
status | string | — | status |
Parameters from the server's own tool schema.
Why fda_recalls is rated Low
Even though fda_recalls only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHigh parameter count (15 properties) · Admin/system-level operation
Attacks that exploit this kind of access
The rule that runs fda_recalls safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ScorpTech x402 API, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fda_recalls, this is the rule to start with:
fda_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 ScorpTech x402 API, apply this rule, and every fda_recalls call is checked against it from then on.
Questions about fda_recalls
FDA recalls (openFDA): drug, device and food enforcement reports (class, status, firm, reason, distribution, lots) plus the device recall database (root cause). Filter by firm, product, class, status, state, dates; count by any field. Newest first. Price: $0.01 USDC per successful call (x402, Solana). Same tool over HTTPS: GET https://scorptech.it.com/api/x402/v1/fda-recalls. It is categorised as a Read tool in the ScorpTech x402 API MCP Server, which means it retrieves data without modifying state.
fda_recalls accepts 12 parameters: to, firm, from, skip, sort, count, limit, state, reason, search, source, status. The full parameter table on this page comes from the server's own tool schema.
Register the ScorpTech x402 API MCP server in PolicyLayer and add a rule for fda_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 ScorpTech x402 API. Nothing to install.
fda_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_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_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_recalls is provided by the ScorpTech x402 API MCP server (https://scorptech.it.com/api/x402/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ScorpTech x402 API, and thousands of servers like it.
This server
Across the catalogue