Get current weather for a city using Open-Meteo API
AI agents call get_current_weather to retrieve information from MCP Weather Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries weather data from an external API and returns information to the user. It has no side effects, does not modify any data, and presents no blast radius if misused by an AI agent—at worst, an agent could make many requests, but no harm results. This is a straightforward Read operation.
From the tool's definition Tool description states 'Get current weather for a city' — a retrieval operation with no modification, creation, or deletion of data. Server description confirms it 'retrieves current conditions' and 'enables AI assistants to retrieve.'
Attacks that exploit this kind of access
Get current weather for a city using Open-Meteo API. It is categorised as a Read tool in the MCP Weather Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Weather Server MCP server in PolicyLayer and add a rule for get_current_weather: 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 Weather Server. Nothing to install.
get_current_weather 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_current_weather 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_current_weather. 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_current_weather is provided by the MCP Weather Server MCP server (kumaran-is/mcp-weather-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 →