AI agents call get_installation to retrieve information from Airly without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries and returns static information about an air quality monitoring installation. There are no side effects, no data modification, and no capability to alter state. The tool falls squarely into the Read category with minimal risk profile.
From the tool's definition Tool retrieves 'metadata for a specific Airly installation' including 'address, coordinates, and sensor type' — pure data retrieval with no mutation, deletion, or execution of operations.
Attacks that exploit this kind of access
Get metadata for a specific Airly installation by its ID, including address, coordinates, and sensor type. It is categorised as a Read tool in the Airly MCP Server, which means it retrieves data without modifying state.
Register the Airly MCP server in PolicyLayer and add a rule for get_installation: 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 Airly. Nothing to install.
get_installation 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_installation 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_installation. 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_installation is provided by the Airly MCP server (jsynowiec/mcp-server-airly). 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 →