Cancel a running automation execution.
AI agents call cancel_execution to permanently remove resources in Qontinui Web MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a running execution is an irreversible action — the in-progress automation is terminated and cannot be resumed. This falls under Destructive as the running state is permanently destroyed. The blast radius is high because cancelling an automation mid-execution could leave systems in inconsistent or partially-completed states.
From the tool's definition Cancel a running automation execution
Attacks that exploit this kind of access
Cancel a running automation execution. It is categorised as a Destructive tool in the Qontinui Web MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Qontinui Web MCP Server MCP server in PolicyLayer and add a rule for cancel_execution: 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 Qontinui Web MCP Server. Nothing to install.
cancel_execution 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_execution 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_execution. 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_execution is provided by the Qontinui Web MCP Server MCP server (qontinui/qontinui-web-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 →