Open a Luxxon session at a lat/lng, push-dispatch the longest-idle operator in range, and wait for the operator to go LIVE. Returns the sessionId either way: if LIVE within timeoutMs, the response includes whepUrl + a hint to call get_frame; if still ASSIGNED/REQUESTED after timeoutMs, the respon...
AI agents use request_live_view to commit financial operations through Luxxon — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The tool explicitly states it 'Charges the workspace' and the server description confirms per-second USDC settlement on Base. This directly commits financial resources. Even on testnet currently, the tool is designed and classified as a financial commitment mechanism. Financial > all other categories.
From the tool's definition 'Charges the workspace' — the tool initiates a billable session settled per-second in USDC on Base, dispatches a live operator, and incurs real financial obligations upon invocation.
Attacks that exploit this kind of access
Open a Luxxon session at a lat/lng, push-dispatch the longest-idle operator in range, and wait for the operator to go LIVE. Returns the sessionId either way: if LIVE within timeoutMs, the response includes whepUrl + a hint to call get_frame; if still ASSIGNED/REQUESTED after timeoutMs, the response includes the sessionId + current state + a hint to call wait_for_live or cancel_session. Only NO_COVERAGE (no operator in range at dispatch time) errors hard. Charges the workspace. It is categorised as a Financial tool in the Luxxon MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Luxxon MCP server in PolicyLayer and add a rule for request_live_view: 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.
request_live_view is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the request_live_view 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 request_live_view. 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.
request_live_view 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.
request_live_view is one line of Luxxon's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →