Cancel a running training job.
AI agents call cancel_training_job to permanently remove resources in NeuronSearchLab — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a running training job is an irreversible action: the in-progress computation, accumulated gradients, and intermediate model state are lost and cannot be recovered. This is effectively a destructive operation as the job cannot be resumed from where it was cancelled. The blast radius is high because aborting a training run can invalidate hours or days of computation and delay production model updates.
From the tool's definition cancel_training_job — 'Cancel a running training job'
Attacks that exploit this kind of access
Cancel a running training job. It is categorised as a Destructive tool in the NeuronSearchLab MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the NeuronSearchLab MCP server in PolicyLayer and add a rule for cancel_training_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 NeuronSearchLab. Nothing to install.
cancel_training_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_training_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_training_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_training_job is provided by the NeuronSearchLab MCP server (neuronsearchlab/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 →