Get a plain-English 5-day weather forecast for a city.
AI agents call get_weekly_forecast to retrieve information from Weather mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns forecast information without creating, modifying, deleting, or executing any operations. It is purely informational and poses minimal risk if misused by an AI agent, as the worst outcome would be fetching weather data for unintended locations.
From the tool's definition Tool description states 'Get a plain-English 5-day weather forecast for a city' — this is a retrieval operation that queries weather data with no side effects or modifications.
Attacks that exploit this kind of access
Get a plain-English 5-day weather forecast for a city. It is categorised as a Read tool in the Weather mcp MCP Server, which means it retrieves data without modifying state.
Register the Weather MCP server in PolicyLayer and add a rule for get_weekly_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 Weather mcp. Nothing to install.
get_weekly_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 get_weekly_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 get_weekly_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.
get_weekly_forecast is provided by the Weather MCP server (tarun-004/weather-mcp-server). 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 →