AI agents use smart_duplicate 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.
This tool creates new instances by duplicating an existing one, which is a reversible write operation. It produces new named copies laid out in a grid pattern. Misuse could clutter the scene with many duplicate objects, but the operation is reversible (copies can be deleted). Severity is medium due to potential bulk creation (multiple copies at once) that could be disruptive if count is large.
From the tool's definition Duplicate with intelligent positioning — auto-names and spaces copies in a grid
Attacks that exploit this kind of access
Duplicate with intelligent positioning — auto-names and spaces copies in a grid. Args: - path (string): Instance to duplicate - count (number): Number of copies - layout (string, optional):. 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 smart_duplicate: 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.
smart_duplicate 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 smart_duplicate 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 smart_duplicate. 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.
smart_duplicate 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 →