AI agents call earth.now 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.
The tool performs only data retrieval and aggregation of publicly available information (time, weather, seismic data). It has no capacity to modify, delete, execute commands, or trigger financial transactions. The lack of side effects, combined with read-only semantics, places it firmly in the Read category with low severity.
From the tool's definition Tool retrieves composite situational awareness data (timezone, local time, sunrise/sunset, nearby quakes, current weather) for a given coordinate. All operations are read-only queries with no side effects, data modification, or external state changes.
Attacks that exploit this kind of access
Composite situational awareness for a coordinate: timezone, local time, sunrise/sunset, nearby quakes, current weather. 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 earth.now: 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.
earth.now 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 earth.now 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 earth.now. 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.
earth.now 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 →