Delete a bank account from sevdesk
AI agents call delete_check_account to permanently remove resources in Sevdesk — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a bank account (check account) from the sevdesk accounting system. Deletion of financial accounts is an irreversible destructive action that cannot be undone and could impact financial records, reconciliation, and business operations. While not directly moving money (which would be Financial), the destruction of a bank account record is a high-severity destructive operation.
From the tool's definition Tool name 'delete_check_account' combined with description 'Delete a bank account from sevdesk' explicitly indicates irreversible deletion of a financial account record.
Attacks that exploit this kind of access
Delete a bank account from sevdesk. It is categorised as a Destructive tool in the Sevdesk MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sevdesk MCP server in PolicyLayer and add a rule for delete_check_account: 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 Sevdesk. Nothing to install.
delete_check_account is a Destructive 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 delete_check_account 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 delete_check_account. 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.
delete_check_account is provided by the Sevdesk MCP server (codestra/sevdesk-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 →