取消 GitLab 流水线
AI agents call cancel_pipeline to permanently remove resources in GitLab Pipeline MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Canceling a pipeline is an irreversible action: the running pipeline is stopped and cannot be resumed. Any in-progress jobs are terminated, deployments or builds that were underway are aborted, and the pipeline state is permanently set to 'canceled'. This cannot be undone — a new pipeline would need to be triggered.
From the tool's definition cancel_pipeline — '取消 GitLab 流水线' (Cancel GitLab pipeline). The server description explicitly lists 'canceling pipelines' as a supported operation.
Attacks that exploit this kind of access
取消 GitLab 流水线. It is categorised as a Destructive tool in the GitLab Pipeline MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the GitLab Pipeline MCP Server 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 Pipeline MCP Server. 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 Pipeline MCP Server MCP server (wqhui/mcp-gitlab). 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 →