Send tokens from a wallet to an arbitrary recipient address (direct ERC-20 transfer)
AI agents use yault_send_payment to commit financial operations through Yault AESP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool moves cryptocurrency tokens (ERC-20) from a wallet to an arbitrary external address. This is a direct financial transaction — irreversible on-chain — with potentially unlimited blast radius if misused by an AI agent sending funds to unintended or malicious addresses. It clearly falls under the Financial category, which is the most severe applicable category.
From the tool's definition Send tokens from a wallet to an arbitrary recipient address (direct ERC-20 transfer)
Attacks that exploit this kind of access
Send tokens from a wallet to an arbitrary recipient address (direct ERC-20 transfer). It is categorised as a Financial tool in the Yault AESP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Yault AESP MCP server in PolicyLayer and add a rule for yault_send_payment: 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 Yault AESP. Nothing to install.
yault_send_payment 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 yault_send_payment 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 yault_send_payment. 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.
yault_send_payment is provided by the Yault AESP MCP server (@yault/aesp). 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 →