CPSC consumer-product recalls (SaferProducts.gov), newest first. Covers everything outside FDA (food/drug/device) and NHTSA (vehicles): strollers, appliances, lithium batteries, furniture, toys, power tools, etc. All filters optional (none set → last 12 months). Each record has recall number+date...
AI agents call gov.product-recalls to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns consumer product recall data from a public government source. It only retrieves information (recall number, date, title, hazards, etc.) and has no write, execute, or financial capabilities. The pay-per-call settlement in USDC is a server-level billing mechanism, not a financial action performed by this specific tool.
From the tool's definition 'CPSC consumer-product recalls (SaferProducts.gov), newest first' — retrieves recall records with filters; read-only data lookup with no side effects
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
CPSC consumer-product recalls (SaferProducts.gov), newest first. Covers everything outside FDA (food/drug/device) and NHTSA (vehicles): strollers, appliances, lithium batteries, furniture, toys, power tools, etc. All filters optional (none set → last 12 months). Each record has recall number+date, title, CPSC URL, affected products, hazards, remedies, injuries, manufacturers/importers/distributors/retailers, where sold, countries, images. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for gov.product-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 Mcp. Nothing to install.
gov.product-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 gov.product-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 gov.product-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.
gov.product-recalls is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →