AI agents use danke_withdraw to commit financial operations through Danke — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool commits financial obligations by transferring cryptocurrency (Bitcoin sats) from the agent's balance to an external Lightning Network address. This is a direct money movement operation. Even though the sats are 'earned' rather than belonging to a user or business directly, the tool enables irreversible transfer of financial value.
From the tool's definition Tool description explicitly states 'Withdraw earned sats to a Lightning Network invoice.' The server description confirms this is a micropayment system on the Bitcoin Lightning Network.
Attacks that exploit this kind of access
Withdraw earned sats to a Lightning Network invoice. It is categorised as a Financial tool in the Danke MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Danke MCP server in PolicyLayer and add a rule for danke_withdraw: 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 Danke. Nothing to install.
danke_withdraw 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 danke_withdraw 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 danke_withdraw. 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.
danke_withdraw is provided by the Danke MCP server (jordiagi/danke-mcp). 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 →