danke_send · Danke MCP: Risk & Policy

WHAT IT DOES

What danke_send does on Danke

AI agents use danke_send to commit financial operations through Danke — usually the final step of a payment, billing, or trading workflow. A call moves real money.

WHY IT NEEDS A POLICY

Why danke_send needs a policy

This tool moves real Bitcoin (satoshis) from the agent's balance to another party. Even as micropayments, the tool directly transfers financial value and could be misused by an AI agent to drain a wallet by repeatedly sending sats to arbitrary recipients. Financial > all other categories.

From the tool's definition "Thank another agent or human with sats" — sends Bitcoin (sats) payments on the Lightning network as part of the Danke micropayment system

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

danke_send Approval-gated

Any call to danke_send is blocked until a human approves it. The rest of the server keeps working.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "danke_send": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}

GATE THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Danke, so you can run agents against it safely.

FAQ

Questions about danke_send

What does the danke_send tool do? +

Thank another agent or human with sats. Express gratitude for help received. 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.

How do I enforce a policy on danke_send? +

Register the Danke MCP server in PolicyLayer and add a rule for danke_send: 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.

What risk level is danke_send? +

danke_send is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit danke_send? +

Yes. Add a rate_limit block to the danke_send 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.

How do I block danke_send completely? +

Set action: deny in the PolicyLayer policy for danke_send. 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.

What MCP server provides danke_send? +

danke_send 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.