Move entities between zones (copy + delete from source).
AI agents use move_entities to create or update resources in Elastic Brain ZH — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Elastic Brain ZH environment.
The operation is a compound write action: it copies entities (reversible write) and deletes from the source (destructive component). However, since the entities still exist in the destination zone, the data is not irreversibly lost—it is moved, not purged. This makes it Write rather than Destructive.
From the tool's definition Tool description states 'Move entities between zones (copy + delete from source)' — performs copy and delete operations sequentially on entity data across memory zones.
Attacks that exploit this kind of access
Move entities between zones (copy + delete from source). It is categorised as a Write tool in the Elastic Brain ZH MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Elastic Brain ZH MCP server in PolicyLayer and add a rule for move_entities: 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 Elastic Brain ZH. Nothing to install.
move_entities 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 move_entities 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 move_entities. 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.
move_entities is provided by the Elastic Brain ZH MCP server (tocharianou/elastic-brain-zh). 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 →