AI agents use end_session to commit financial operations through Luxxon — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Ending a live session triggers an on-chain financial settlement in USDC on Base, committing a financial obligation based on the number of seconds used. This is a financial action because it finalizes and settles payment, making it the most severe applicable category.
From the tool's definition Closes the meter; computes cleanSeconds; the relayer settles on-chain shortly after
Attacks that exploit this kind of access
End a LIVE Luxxon session. Closes the meter; computes cleanSeconds; the relayer settles on-chain shortly after. For pre-LIVE sessions use cancel_session instead. 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 end_session: 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.
end_session 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 end_session 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 end_session. 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.
end_session 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 →