Close a batch after all tasks have been submitted.
AI agents use close_batch to create or update resources in Hive — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hive environment.
This tool creates or modifies data reversibly by changing batch status—characteristic of Write category. It has minimal blast radius (affects only batch metadata state, not data or financial systems) and is reversible, so severity is low. Confidence is 0.8 because the description is brief but the function is clear from context within a task distribution system.
From the tool's definition The tool 'close_batch' operates on batch state management. It closes/modifies the status of a batch object after task submission is complete.
Documented attack patterns abuse exactly the kind of access close_batch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hive, and nothing reaches the server without passing your rules. This is the rule we recommend for close_batch:
{
"version": "1",
"default": "deny",
"tools": {
"close_batch": {
"limits": [
{
"counter": "close_batch_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}close_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.
Close a batch after all tasks have been submitted. It is categorised as a Write tool in the Hive MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hive MCP server in PolicyLayer and add a rule for close_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 Hive. Nothing to install.
close_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 close_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 close_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.
close_batch is provided by the Hive MCP server (saikodi/hive-compute-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Hive, 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.
12 Hive tools catalogued and risk-classified — across an index of 43,000+ MCP servers.