AI agents use update_subaccount to create or update resources in Seven — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Seven environment.
This tool modifies subaccount settings reversibly rather than destroying them, placing it in Write category. However, the modification concerns automatic balance transfer configuration, which has financial implications (movement of account credits/funds). Severity is high because misconfiguration could result in unintended fund transfers or loss of financial control.
From the tool's definition Tool name 'update_subaccount' with description 'Configure automatic balance transfer for a subaccount' performs modification of subaccount configuration.
Attacks that exploit this kind of access
Configure automatic balance transfer for a subaccount. It is categorised as a Write tool in the Seven MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Seven MCP server in PolicyLayer and add a rule for update_subaccount: 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.
update_subaccount is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_subaccount 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 update_subaccount. 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.
update_subaccount 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 →