Withdraw money from a savings goal
AI agents use savings_goal_withdraw to commit financial operations through Starling Bank — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool commits a financial obligation by moving money out of a savings goal, which is a core financial operation. Even though the withdrawal itself is technically reversible (money can be re-deposited), the tool's primary function is to move funds, placing it squarely in the Financial category.
From the tool's definition Tool name 'savings_goal_withdraw' and description 'Withdraw money from a savings goal' directly indicate movement of money from a user's account. Starling Bank context confirms this is a financial institution where money movement is irreversible once executed.
Attacks that exploit this kind of access
Withdraw money from a savings goal. It is categorised as a Financial tool in the Starling Bank MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Starling Bank MCP server in PolicyLayer and add a rule for savings_goal_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 Starling Bank. Nothing to install.
savings_goal_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 savings_goal_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 savings_goal_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.
savings_goal_withdraw is provided by the Starling Bank MCP server (starling-bank-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 →