Cancel a running pipeline.
AI agents call cancel_pipeline to permanently remove resources in GitLab MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a pipeline is not easily reversible: jobs that were running are killed, deployment steps are aborted, and any side effects already applied by those jobs cannot be undone. While the pipeline record itself remains visible, the execution state cannot be resumed. This makes it closer to Destructive than Execute, with a high blast radius if a production deployment pipeline is cancelled mid-run.
From the tool's definition 'Cancel a running pipeline' — cancels an in-progress CI/CD pipeline, which irreversibly terminates the execution and any associated jobs/deployments that were running.
Attacks that exploit this kind of access
Cancel a running pipeline. It is categorised as a Destructive tool in the GitLab MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GitLab MCP server in PolicyLayer and add a rule for cancel_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 GitLab MCP. Nothing to install.
cancel_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 cancel_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 cancel_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.
cancel_pipeline is provided by the GitLab MCP server (shahabmosavi/gitlab_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 →