WATCHER: get a signed callback when USGS reports a new earthquake near a location above a magnitude. Arm once, pay once. Pass lat, lon, optional radiusKm (default 500) and minMagnitude (default 4). Fires once per new quake (deduped by id); bounded by maxFires/expiry. Quakes already in the window ...
AI agents invoke watchers.earthquake to trigger actions in Mcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool registers a standing trigger that executes signed callbacks on external events. While payment is mentioned ('pay once'), the financial component is a one-time setup fee rather than an ongoing financial transaction — the core action is executing a callback when conditions are met. The persistent nature and external callback execution place this in the Execute category.
From the tool's definition 'get a signed callback when USGS reports a new earthquake near a location' — arms a persistent watcher that triggers external callback operations repeatedly ('Fires once per new quake'); 'Arm once, pay once' and 'pay-per-call tools settled in USDC' indicate…
Attacks that exploit this kind of access
WATCHER: get a signed callback when USGS reports a new earthquake near a location above a magnitude. Arm once, pay once. Pass lat, lon, optional radiusKm (default 500) and minMagnitude (default 4). Fires once per new quake (deduped by id); bounded by maxFires/expiry. Quakes already in the window at arm time are baselined. Free public-domain (USGS). Signed + retried; recoverable via watchers.status. It is categorised as a Execute tool in the Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP server in PolicyLayer and add a rule for watchers.earthquake: 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.earthquake is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the watchers.earthquake 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.earthquake. 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.earthquake 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 →