Cancel a running stage and all its jobs immediately. Use this to stop a long-running stage, abort a deployment that
AI agents call cancel_stage to permanently remove resources in GoCD MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a running stage and all its jobs is an irreversible action — the in-progress execution is terminated immediately and cannot be undone. This can abort deployments mid-flight, potentially leaving systems in an inconsistent state, which warrants a high severity rating.
From the tool's definition Cancel a running stage and all its jobs immediately... abort a deployment
Attacks that exploit this kind of access
Cancel a running stage and all its jobs immediately. Use this to stop a long-running stage, abort a deployment that. It is categorised as a Destructive tool in the GoCD MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GoCD MCP Server MCP server in PolicyLayer and add a rule for cancel_stage: 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 GoCD MCP Server. Nothing to install.
cancel_stage 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 cancel_stage 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 cancel_stage. 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.
cancel_stage is provided by the GoCD MCP Server MCP server (rushi/gocd-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 →