delete_work_item
AI agents call delete_work_item to permanently remove resources in Ado — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool name 'delete_work_item' combined with context of Azure DevOps work item management indicates this performs irreversible deletion of work items. Even without a description, the semantic meaning of 'delete' in this context is unambiguous—it permanently removes data that cannot be recovered through normal means. This is more severe than Write (which is reversible) and falls into Destructive category.
From the tool's definition Tool name is 'delete_work_item' and sibling tool 'delete_work_items_batch' exists, indicating irreversible deletion capability. Description is empty but naming convention strongly indicates permanent data removal.
Attacks that exploit this kind of access
delete_work_item. It is categorised as a Destructive tool in the Ado MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ado MCP server in PolicyLayer and add a rule for delete_work_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 Ado. Nothing to install.
delete_work_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_work_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_work_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_work_item is provided by the Ado MCP server (raboley/ado-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 →