actual_categories_delete
Delete a category from Actual Budget. Transactions using this category will need to be recategorized. This operation cannot be undone.
This record as markdown: /tools/actual/actual-categories-delete.md
What actual_categories_delete does on Actual
AI agents call actual_categories_delete to permanently remove resources in Actual, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why actual_categories_delete is rated Critical
This tool irreversibly deletes a category, forcing dependent transactions to be manually recategorized. While the financial impact is indirect (no money moves), the data destruction is permanent and affects the integrity of financial records. This qualifies as Destructive rather than Write because the action cannot be reversed.
From the tool's definition Tool description states "Delete a category from Actual Budget" and explicitly warns "This operation cannot be undone." The word "Delete" combined with the irreversible nature makes this destructive.
Attacks that exploit this kind of access
The rule that runs actual_categories_delete safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Actual, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For actual_categories_delete, this is the rule to start with:
actual_categories_delete is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Actual, apply this rule, and every actual_categories_delete call is checked against it from then on.
Questions about actual_categories_delete
Delete a category from Actual Budget. Transactions using this category will need to be recategorized. This operation cannot be undone. It is categorised as a Destructive tool in the Actual MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Actual MCP server in PolicyLayer and add a rule for actual_categories_delete: 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 Actual. Nothing to install.
actual_categories_delete 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 actual_categories_delete 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 actual_categories_delete. 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.
actual_categories_delete is provided by the Actual MCP server (actual-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Actual, and thousands of servers like it.
Across the catalogue