AI agents call getWeather to retrieve information from Mcp Lite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Weather data retrieval has no side effects and aligns with the Read category (query/fetch semantics). Low severity due to minimal blast radius—weather data is non-sensitive and read-only. Confidence reduced to 0.7 because the empty description prevents direct confirmation of actual behavior; however, the naming pattern and server context make Read highly likely.
From the tool's definition Tool name 'getWeather' suggests data retrieval; description is empty, limiting certainty. Sibling tools include 'getConfig' (clearly Read) and 'ping' (diagnostic), supporting a Read classification for similar getter-pattern tools.
Attacks that exploit this kind of access
getWeather. It is categorised as a Read tool in the Mcp Lite MCP Server, which means it retrieves data without modifying state.
Register the Mcp Lite MCP server in PolicyLayer and add a rule for getWeather: 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 Lite. Nothing to install.
getWeather 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 getWeather 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 getWeather. 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.
getWeather is provided by the Mcp Lite MCP server (mcp-lite). 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 →