Makes all your unconfirmed transactions use a higher fee rate, using CPFP. Returns the ID of the child transaction
AI agents use bump-fee 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 commits additional Bitcoin fees by creating a child transaction (CPFP) that increases the fee rate for unconfirmed transactions. This constitutes a financial commitment — spending additional on-chain Bitcoin fees — and is irreversible once the child transaction is broadcast. The blast radius is high since it affects ALL unconfirmed transactions simultaneously and commits real funds.
From the tool's definition Makes all your unconfirmed transactions use a higher fee rate, using CPFP
Attacks that exploit this kind of access
Makes all your unconfirmed transactions use a higher fee rate, using CPFP. Returns the ID of the child transaction. 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 bump-fee: 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.
bump-fee 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 bump-fee 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 bump-fee. 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.
bump-fee 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 →