Pay an on-chain address with a specified amount and fee rate
AI agents use pay-on-chain to commit financial operations through Phoenixd MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly commits financial obligations by transferring on-chain Bitcoin to a specified address. The action is irreversible—once confirmed on the blockchain, the transaction cannot be undone. An AI agent with access to this tool could drain wallet funds if prompt injection or model confusion occurs.
From the tool's definition Tool name 'pay-on-chain' combined with description 'Pay an on-chain address with a specified amount and fee rate' indicates irreversible transfer of Bitcoin funds.
Attacks that exploit this kind of access
Pay an on-chain address with a specified amount and fee rate. It is categorised as a Financial tool in the Phoenixd MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Phoenixd MCP Server MCP server in PolicyLayer and add a rule for pay-on-chain: 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 Phoenixd MCP Server. Nothing to install.
pay-on-chain 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 pay-on-chain 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 pay-on-chain. 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.
pay-on-chain is provided by the Phoenixd MCP Server MCP server (sharmaz/phoenixd-mcp-server). 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 →