recall_screen
One-call product-safety recall sweep across CPSC (consumer products), openFDA (drug/device/food enforcement), and NHTSA (vehicles). Provide a product/keyword/manufacturer query and/or a full vehicle (year+make+model). Results are normalized, deduped within and across sources, severity-rolled (FDA...
This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/recall-screen.md
What recall_screen does on Livedatalink
AI agents call recall_screen to retrieve information from Livedatalink 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 |
|---|---|---|---|
query | string | — | Product, keyword, or manufacturer to screen (e.g. 'infant formula', 'Acme Corp'). |
since | string | — | Optional lower-bound date (YYYY-MM-DD) for FDA recalls. |
domains | array | — | Optional subset of sources to check; default checks all applicable. |
vehicle_make | string | — | Vehicle make (e.g. 'Toyota'). |
vehicle_year | number | — | Vehicle model year (required with make+model for NHTSA). |
vehicle_model | string | — | Vehicle model (e.g. 'Camry'). |
Parameters from the server's own tool schema.
Why recall_screen is rated Low
Even though recall_screen 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.
Attacks that exploit this kind of access
The rule that runs recall_screen safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livedatalink, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For recall_screen, this is the rule to start with:
recall_screen 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 Livedatalink, apply this rule, and every recall_screen call is checked against it from then on.
Questions about recall_screen
One-call product-safety recall sweep across CPSC (consumer products), openFDA (drug/device/food enforcement), and NHTSA (vehicles). Provide a product/keyword/manufacturer query and/or a full vehicle (year+make+model). Results are normalized, deduped within and across sources, severity-rolled (FDA Class I or death-related = high), and summarized with a by-classification breakdown. A source that fails is noted, not fatal. Premium cross-source synthesis. Verify against the official sources before acting. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.
recall_screen accepts 6 parameters: query, since, domains, vehicle_make, vehicle_year, vehicle_model. The full parameter table on this page comes from the server's own tool schema.
Register the Livedatalink MCP server in PolicyLayer and add a rule for recall_screen: 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 Livedatalink. Nothing to install.
recall_screen 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 recall_screen 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 recall_screen. 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.
recall_screen is provided by the Livedatalink MCP server (https://livedatalink.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Livedatalink, and thousands of servers like it.
This server
Across the catalogue