Fetch significant recent earthquakes from USGS (United States Geological Survey): magnitude, epicentre location, depth, affected region, and tsunami watch/warning status. Use this tool when: - A risk agent is monitoring for seismic events that could disrupt infrastructure or supply chains - An in...
AI agents call get_earthquake_monitor to retrieve information from Omni Service Node without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves public seismic data from USGS with no side effects. It queries an external data source and returns structured information for analysis and monitoring purposes. The use cases (risk monitoring, insurance assessment, geopolitical correlation) all involve data consumption only. No irreversible actions, financial transactions, or command execution are possible through this interface.
From the tool's definition Tool description states 'Fetch significant recent earthquakes from USGS' with return fields: magnitude, location, depth_km, coordinates. No creation, modification, deletion, code execution, or financial operations are described.
Attacks that exploit this kind of access
Fetch significant recent earthquakes from USGS (United States Geological Survey): magnitude, epicentre location, depth, affected region, and tsunami watch/warning status. Use this tool when: - A risk agent is monitoring for seismic events that could disrupt infrastructure or supply chains - An insurance or catastrophe risk agent needs real-time earthquake data - You want to assess whether an earthquake could cause a tsunami (Pacific Rim events) - A geopolitical risk agent is correlating natural disasters with economic disruption Returns per event: magnitude, location, depth_km, coordinates, time_utc, tsunami_warning (YES/NO), affected_region, USGS_url, economic_impact_estimate. Example: getEarthquakeMonitor({ days: 7, minMagnitude: 6.0 }) → M6.8 in Japan Sea (47km depth), no tsunami warning. Cost: $0.005 USDC per call. It is categorised as a Read tool in the Omni Service Node MCP Server, which means it retrieves data without modifying state.
Register the Omni Service Node MCP server in PolicyLayer and add a rule for get_earthquake_monitor: 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 Omni Service Node. Nothing to install.
get_earthquake_monitor 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 get_earthquake_monitor 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 get_earthquake_monitor. 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.
get_earthquake_monitor is provided by the Omni Service Node MCP server (luckkyyy23/omni-service-node). 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 →