AI agents use create_batch to create or update resources in Gpal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gpal environment.
The 'create_batch' tool most likely creates batch job records or configurations for processing, which constitutes data creation and modification (Write category). While the empty description reduces certainty, the presence of paired delete and cancel operations on the same server suggests reversible batch lifecycle management rather than destructive operations.
From the tool's definition Tool name 'create_batch' combined with sibling tools 'cancel_batch' and 'delete_batch' indicates batch management operations. The naming pattern (create/delete/cancel) suggests data creation and lifecycle management. Description is empty, limiting confidence.
Documented attack patterns abuse exactly the kind of access create_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 create_batch:
{
"version": "1",
"default": "deny",
"tools": {
"create_batch": {
"limits": [
{
"counter": "create_batch_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_batch stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
create_batch. It is categorised as a Write tool in the Gpal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gpal MCP server in PolicyLayer and add a rule for create_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.
create_batch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_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.