WATCHER: get a signed callback when a new US product recall is published (CPSC). Arm once, pay once. Optionally pass keyword to only fire on recalls whose title contains it (e.g. a brand or product). Fires once per new recall (deduped by recall id); bounded by maxFires/expiry. Existing recalls at...
AI agents call watchers.product-recall 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 is fundamentally a Read operation—it retrieves and delivers publicly available recall data via callback subscription. The tool does not create, modify, delete, or execute arbitrary code. The financial aspect (pay-per-call via x402) is the payment mechanism for the service itself, not the tool's primary function.
From the tool's definition The tool 'gets a signed callback when a new US product recall is published' and retrieves 'free public-domain data' from CPSC.
Attacks that exploit this kind of access
WATCHER: get a signed callback when a new US product recall is published (CPSC). Arm once, pay once. Optionally pass keyword to only fire on recalls whose title contains it (e.g. a brand or product). Fires once per new recall (deduped by recall id); bounded by maxFires/expiry. Existing recalls at arm time are baselined. Free public-domain data. Signed (verify offline) + retried; recoverable via wa. 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 watchers.product-recall: 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.
watchers.product-recall 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 watchers.product-recall 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 watchers.product-recall. 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.
watchers.product-recall 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 →