Archive or delete an item in Sanka by item id or external reference.
AI agents call delete_item to permanently remove resources in Sanka MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool directly deletes or archives items, which destroys data and cannot be undone. Even though archiving may be reversible in some systems, the explicit mention of 'delete' combined with the Destructive category rules (irreversibly deletes or overwrites data) places this at Destructive severity.
From the tool's definition Tool explicitly performs 'delete' operation on items; description states it can 'Archive or delete an item' which indicates irreversible data removal capability.
Attacks that exploit this kind of access
Archive or delete an item in Sanka by item id or external reference. It is categorised as a Destructive tool in the Sanka MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sanka MCP Server MCP server in PolicyLayer and add a rule for delete_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 Sanka MCP Server. Nothing to install.
delete_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_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_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_item is provided by the Sanka MCP Server MCP server (sankahq/sanka-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 →