AI agents use transfer_credits to commit financial operations through Seven — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves credits (a form of currency/financial value) from one account to another, which constitutes a financial transaction. Even though it targets a subaccount rather than external entities, it commits financial obligations and changes account balances. Misuse by an AI agent could result in unauthorized depletion of account credits or improper distribution of funds.
From the tool's definition Tool name 'transfer_credits' and description 'Manually transfer credits to a subaccount' explicitly indicate movement of financial resources (credits) between accounts.
Attacks that exploit this kind of access
Manually transfer credits to a subaccount. It is categorised as a Financial tool in the Seven MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Seven MCP server in PolicyLayer and add a rule for transfer_credits: 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 Seven. Nothing to install.
transfer_credits 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 transfer_credits 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 transfer_credits. 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.
transfer_credits is provided by the Seven MCP server (seven-io/seven-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 →