Delete a DICT item from a file
AI agents call delete_dict_item to permanently remove resources in UOFastMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on dictionary items in a database file. Deletion cannot be undone without backups, and in a database context, the blast radius includes loss of schema/metadata definitions that other operations depend on. This is a Destructive action rather than merely Write.
From the tool's definition Tool name 'delete_dict_item' and description 'Delete a DICT item from a file' indicate irreversible deletion of data from a U2 UniData/UniVerse database dictionary.
Attacks that exploit this kind of access
Delete a DICT item from a file. It is categorised as a Destructive tool in the UOFastMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the UOFast MCP server in PolicyLayer and add a rule for delete_dict_item: 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 UOFastMCP. Nothing to install.
delete_dict_item 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_dict_item 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_dict_item. 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_dict_item is provided by the UOFast MCP server (rokipark/uofastmcp). 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 →