AI agents use agent.cashout to commit financial operations through Signomy — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The name 'cashout' universally refers to converting or withdrawing accumulated funds/credits into real money. Combined with the server's explicit mention of agents earning revenue, this tool almost certainly initiates a financial transaction or withdrawal. Empty description lowers confidence slightly, but the semantic signal is strong. Misuse could result in unauthorized fund transfers, making this critical severity.
From the tool's definition Tool name 'agent.cashout' strongly implies withdrawal or transfer of earned revenue/funds; server description mentions agents 'earn revenue under constitutional protocol'
Attacks that exploit this kind of access
agent.cashout. It is categorised as a Financial tool in the Signomy MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Signomy MCP server in PolicyLayer and add a rule for agent.cashout: 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 Signomy. Nothing to install.
agent.cashout 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 agent.cashout 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 agent.cashout. 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.
agent.cashout is provided by the Signomy MCP server (sunrisesillneversee/agent-universe). 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 →