Delete a transaction by creating a reversing transaction. Original is not hard-deleted.
AI agents use delete_transaction to create or update resources in Finance App — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Finance App environment.
Despite being named 'delete', this tool works by creating a reversing/offsetting transaction — a standard double-entry accounting technique. Since the original transaction is preserved and a new reversing entry is created, the operation is reversible and falls under Write rather than Destructive. The financial data is not permanently removed.
From the tool's definition Delete a transaction by creating a reversing transaction. Original is not hard-deleted.
Attacks that exploit this kind of access
Delete a transaction by creating a reversing transaction. Original is not hard-deleted. It is categorised as a Write tool in the Finance App MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Finance App MCP server in PolicyLayer and add a rule for delete_transaction: 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 Finance App. Nothing to install.
delete_transaction 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 delete_transaction 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_transaction. 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_transaction is provided by the Finance App MCP server (youssefaltai/finance-app). 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 →