delete_pipeline
AI agents call delete_pipeline 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.
Pipeline deletion cannot be undone and eliminates CI/CD infrastructure, build definitions, and associated history. This is the most severe category (Destructive) applicable. High severity reflects the blast radius of accidentally deleting critical build pipelines in an organization's DevOps infrastructure. Confidence is high despite missing description because the function name is explicit and unambiguous.
From the tool's definition Tool name is 'delete_pipeline' with no description provided. The name unambiguously indicates deletion of Azure DevOps pipelines, which is an irreversible destructive action.
Attacks that exploit this kind of access
delete_pipeline. 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_pipeline: 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_pipeline 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_pipeline 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_pipeline. 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_pipeline 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 →