Cancel a queued or running job.
AI agents call boltzgen_cancel_job to permanently remove resources in BoltzGen MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a job is irreversible — once cancelled, the job's progress and intermediate results are lost and cannot be recovered. This matches the Destructive category as the action cannot be undone. Severity is medium because it affects computational jobs rather than persistent data, but misuse could waste resources and destroy in-progress protein design work.
From the tool's definition Cancel a queued or running job
Attacks that exploit this kind of access
Cancel a queued or running job. It is categorised as a Destructive tool in the BoltzGen MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the BoltzGen MCP server in PolicyLayer and add a rule for boltzgen_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 BoltzGen MCP. Nothing to install.
boltzgen_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 boltzgen_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 boltzgen_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.
boltzgen_cancel_job is provided by the BoltzGen MCP server (macromnex/boltzgen_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 →