AI agents call weather.air-quality to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns air quality data from the Open-Meteo/CAMS service based on geographic coordinates. It performs a pure read operation with no capability to modify state, execute code, destroy data, or commit financial transactions. The pay-per-call USDC settlement is a billing mechanism, not a capability of the tool itself.
From the tool's definition Tool description states it provides 'Current air quality for any coordinate worldwide' with specific metrics (AQI, PM2.5, PM10, ozone, NO2, SO2, CO concentrations).
Attacks that exploit this kind of access
Current air quality for any coordinate worldwide: US AQI (+ category) and European AQI, plus PM2.5, PM10, ozone, NO2, SO2, CO concentrations. Source: Open-Meteo/CAMS (keyless). It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for weather.air-quality: 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. Nothing to install.
weather.air-quality 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 weather.air-quality 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 weather.air-quality. 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.
weather.air-quality is provided by the MCP server (@2sio/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 →