Delete a single item from a collection
AI agents call delete_collection_item to permanently remove resources in AI-Canvas MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from a collection without the ability to undo the operation. While the blast radius is scoped to a single item (not bulk deletion), the irreversible nature of deletion and the design context (where collections likely contain valuable design assets or configurations) justifies a 'high' severity.
From the tool's definition Tool name is 'delete_collection_item' and description states 'Delete a single item from a collection'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a single item from a collection. It is categorised as a Destructive tool in the AI-Canvas MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AI-Canvas MCP Server MCP server in PolicyLayer and add a rule for delete_collection_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 AI-Canvas MCP Server. Nothing to install.
delete_collection_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_collection_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_collection_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_collection_item is provided by the AI-Canvas MCP Server MCP server (laoluojuhai/ai-canvas). 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 →