AI agents call get_weather_by_city to retrieve information from Mcp Meteo 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 current weather information for a specified city. It performs a read-only operation with no data modification, deletion, code execution, or financial implications. The low severity reflects minimal blast radius if misused by an AI agent—worst case would be repeated queries consuming API quota.
From the tool's definition Tool name contains 'get_' prefix and description states 'Météo actuelle pour une ville donnée' (Current weather for a given city), which retrieves real-time weather data without modification or side effects.
Attacks that exploit this kind of access
Météo actuelle pour une ville donnée. It is categorised as a Read tool in the Mcp Meteo MCP Server, which means it retrieves data without modifying state.
Register the Mcp Meteo MCP server in PolicyLayer and add a rule for get_weather_by_city: 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 Meteo. Nothing to install.
get_weather_by_city 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_weather_by_city 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_weather_by_city. 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_weather_by_city is provided by the Mcp Meteo MCP server (kerryanopmace/mcp-meteo). 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 →