AI agents call get_historical_rainfall to retrieve information from Roc Cwa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves weather/rainfall data without side effects. It does not create, modify, delete, or execute any operations—it merely fetches historical information. The low severity reflects minimal blast radius: misuse would only result in unauthorized data access to public weather records, not system compromise or data loss.
From the tool's definition Tool retrieves historical rainfall data ('Get rainfall data for the past three days') with no modification or deletion capability; consistent with sibling tools (get_1_week_weather, get_3_days_weather) which are forecasting/data retrieval functions.
Attacks that exploit this kind of access
Get rainfall data for the past three days. It is categorised as a Read tool in the Roc Cwa MCP Server, which means it retrieves data without modifying state.
Register the Roc Cwa MCP server in PolicyLayer and add a rule for get_historical_rainfall: 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 Roc Cwa. Nothing to install.
get_historical_rainfall 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_historical_rainfall 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_historical_rainfall. 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_historical_rainfall is provided by the Roc Cwa MCP server (lwsinclair/roc-cwa-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 →