send_money
AI agents use send_money to commit financial operations through Wise MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The server description makes clear this server moves real money via the Wise API. A tool named 'send_money' on such a server almost certainly initiates financial transfers. Even with an empty tool description, the combination of the server context and the tool name strongly indicates this is a financial action that moves funds, which is irreversible and carries critical blast radius if misused.
From the tool's definition Tool name 'send_money' on a server explicitly described as 'sending money transfers' and 'executing money transfers with authentication handling'
Attacks that exploit this kind of access
send_money. It is categorised as a Financial tool in the Wise MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Wise MCP Server MCP server in PolicyLayer and add a rule for send_money: 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 Wise MCP Server. Nothing to install.
send_money 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 send_money 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 send_money. 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.
send_money is provided by the Wise MCP Server MCP server (sergeiledvanov/mcp-wise). 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 →