AI agents call sg_weather_forecast to retrieve information from Sgdata without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple data retrieval operation on public weather forecast data. There are no side effects, no data modification, no code execution, and no financial implications. The worst-case misuse (e.g., using weather data for spam or deception) has minimal blast radius compared to other risk categories. Classified as Read with low severity.
From the tool's definition Tool queries NEA weather forecast data for Singapore - a read-only operation that retrieves publicly available meteorological information.
Attacks that exploit this kind of access
NEA weather forecast for Singapore. By default returns the 2-hour. It is categorised as a Read tool in the Sgdata MCP Server, which means it retrieves data without modifying state.
Register the Sgdata MCP server in PolicyLayer and add a rule for sg_weather_forecast: 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 Sgdata. Nothing to install.
sg_weather_forecast 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 sg_weather_forecast 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 sg_weather_forecast. 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.
sg_weather_forecast is provided by the Sgdata MCP server (sypherin/sgdata-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 →