Cancel a running job.
AI agents call cancel_job to permanently remove resources in BindCraft MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a running job is an irreversible action: the job's execution state, partial results, and computational progress are lost and cannot be restored. This fits the Destructive category. Severity is medium because while the job itself is lost, no persistent data store is deleted and the job could potentially be resubmitted.
From the tool's definition 'Cancel a running job' — cancelling a job irreversibly terminates an ongoing computation; the job's progress and intermediate results cannot be recovered.
Attacks that exploit this kind of access
Cancel a running job. It is categorised as a Destructive tool in the BindCraft MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the BindCraft MCP server in PolicyLayer and add a rule for cancel_job: 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 BindCraft MCP. Nothing to install.
cancel_job 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 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. 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 is provided by the BindCraft MCP server (macromnex/bindcraft_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 →