Clone an instance and all its children. Args: - path (string): Path to the instance to clone - parent (string, optional): Parent path for the clone (defaults to same parent) - name (string, optional): Name for the cloned instance Returns: { path, name, className } of the cloned instance.
AI agents use clone_object to create or update resources in Melo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Melo environment.
Cloning creates a new copy of an existing instance (and its children) in the hierarchy. This is a reversible write operation — the clone can be deleted afterward. No data is destroyed, no code is executed arbitrarily, and no financial action occurs. Severity is medium because bulk-cloning deeply nested hierarchies could significantly alter the scene, but it remains reversible.
From the tool's definition Clone an instance and all its children
Attacks that exploit this kind of access
Clone an instance and all its children. Args: - path (string): Path to the instance to clone - parent (string, optional): Parent path for the clone (defaults to same parent) - name (string, optional): Name for the cloned instance Returns: { path, name, className } of the cloned instance. It is categorised as a Write tool in the Melo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Melo MCP server in PolicyLayer and add a rule for clone_object: 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 Melo. Nothing to install.
clone_object 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 clone_object 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 clone_object. 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.
clone_object is provided by the Melo MCP server (yannyhl/linkedsword-mcp). 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 →