Cancel a specific job.
AI agents call cancel_job_tool to permanently remove resources in Qiskit Documentation MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a job permanently stops its execution with no ability to undo the cancellation. This is an irreversible action (the job run is lost), placing it in the Destructive category. The blast radius is high because it can terminate potentially long-running or expensive quantum computing jobs on IBM Quantum instances.
From the tool's definition Cancel a specific job — cancellation is an irreversible termination of a running job; the cancelled execution cannot be resumed.
Attacks that exploit this kind of access
Cancel a specific job. It is categorised as a Destructive tool in the Qiskit Documentation MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Qiskit Documentation MCP Server MCP server in PolicyLayer and add a rule for cancel_job_tool: 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 Qiskit Documentation MCP Server. Nothing to install.
cancel_job_tool 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_job_tool 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_job_tool. 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_job_tool is provided by the Qiskit Documentation MCP Server MCP server (pypi:qiskit-mcp-server). 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 →