Cancel a running batch job. Already-completed requests are unaffected.
AI agents invoke cancel_batch to trigger actions in Gpal. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Cancelling a running batch job is an operational action that interrupts an in-progress process. It's not purely destructive (data is not deleted), not a read, and not a write of data. It triggers an external operation (stopping a batch job), making Execute the most appropriate category. Severity is medium as cancelling a batch job could disrupt ongoing work but is generally recoverable.
From the tool's definition Cancel a running batch job. Already-completed requests are unaffected.
Documented attack patterns abuse exactly the kind of access cancel_batch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gpal, and nothing reaches the server without passing your rules. This is the rule we recommend for cancel_batch:
{
"version": "1",
"default": "deny",
"tools": {
"cancel_batch": {
"limits": [
{
"counter": "cancel_batch_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cancel_batch stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Cancel a running batch job. Already-completed requests are unaffected. It is categorised as a Execute tool in the Gpal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gpal MCP server in PolicyLayer and add a rule for cancel_batch: 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 Gpal. Nothing to install.
cancel_batch is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cancel_batch 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_batch. 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_batch is provided by the Gpal MCP server (tobert/gpal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gpal, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 Gpal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.