WATCHER: get a signed callback when the US National Weather Service issues a new alert for an area. Arm once, pay once. Pass area (2-letter state/territory code, e.g. CA, TX); optionally severity to only fire at/above a level (Minor/Moderate/Severe/Extreme). Fires once per new alert (deduped by i...
AI agents call watchers.weather-alert 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 the National Weather Service API and delivers alerts via callback. It reads publicly available weather alert data, applies optional filters, and notifies the caller. No data is created, modified, deleted, or executed in the target system. The financial component (pay-per-call via x402) is incidental infrastructure, not a direct financial action by the tool itself.
From the tool's definition Tool description: 'get a signed callback when the US National Weather Service issues a new alert for an area' — retrieves alert data from a public service with no side effects.
Attacks that exploit this kind of access
WATCHER: get a signed callback when the US National Weather Service issues a new alert for an area. Arm once, pay once. Pass area (2-letter state/territory code, e.g. CA, TX); optionally severity to only fire at/above a level (Minor/Moderate/Severe/Extreme). Fires once per new alert (deduped by id); bounded by maxFires/expiry. Active alerts at arm time are baselined. Free public-domain (NWS). Sign. 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.weather-alert: 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.weather-alert 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.weather-alert 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.weather-alert. 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.weather-alert 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 →