AI agents call get_coverage to retrieve information from Luxxon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries static geographic and device coverage metadata with no side effects. It does not create, modify, delete, or execute operations. While the server involves financial settlement (USDC on Base), this particular tool performs only a read operation to inform subsequent decisions. The data is anonymized and public, presenting minimal risk even if queried by an agent without constraints.
From the tool's definition Tool returns a 'public list' of coverage circles with location data and device information. No modification, deletion, execution of external code, or financial transaction occurs.
Attacks that exploit this kind of access
Public list of live operator coverage circles (centroid + radius + device kind). Anonymized — no operator ids. Useful as a pre-flight check before request_live_view. It is categorised as a Read tool in the Luxxon MCP Server, which means it retrieves data without modifying state.
Register the Luxxon MCP server in PolicyLayer and add a rule for get_coverage: 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 Luxxon. Nothing to install.
get_coverage 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_coverage 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_coverage. 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_coverage is provided by the Luxxon MCP server (luxxon-dev/luxxon-sdk). 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 →