Release a claimed batch without providing mock data. Use this if you cannot generate appropriate mocks.
AI agents use release_batch to create or update resources in Mock — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mock environment.
Releasing a batch modifies the state of a claimed batch (returning it to an unclaimed or available state) without deleting it. This is a reversible state change — the batch still exists and can be reclaimed — making it a Write operation. Misuse could disrupt testing workflows by releasing batches prematurely, but it does not destroy data irreversibly.
From the tool's definition Release a claimed batch without providing mock data. Use this if you cannot generate appropriate mocks.
Documented attack patterns abuse exactly the kind of access release_batch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mock, and nothing reaches the server without passing your rules. This is the rule we recommend for release_batch:
{
"version": "1",
"default": "deny",
"tools": {
"release_batch": {
"limits": [
{
"counter": "release_batch_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}release_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.
Release a claimed batch without providing mock data. Use this if you cannot generate appropriate mocks. It is categorised as a Write tool in the Mock MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mock MCP server in PolicyLayer and add a rule for release_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 Mock. Nothing to install.
release_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 release_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 release_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.
release_batch is provided by the Mock MCP server (mcpland/mock-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mock, 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.
6 Mock tools catalogued and risk-classified — across an index of 43,000+ MCP servers.