Add money to a savings goal
AI agents use savings_goal_deposit 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 moves money (deposits funds into a savings goal), which constitutes a financial transaction. Even though the amount and destination are presumably constrained to the user's own savings goals, any tool that transfers funds represents the highest severity risk category (Financial), as misuse by an AI agent could deplete accounts or commit unintended spending.
From the tool's definition Tool name 'savings_goal_deposit' and description 'Add money to a savings goal' directly indicate movement of money from the user's account.
Attacks that exploit this kind of access
Add money to 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_deposit: 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_deposit 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_deposit 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_deposit. 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_deposit 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 →