AI agents use add_tag 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 modifies instance state by adding tags, which is a write operation. It is reversible (tags can be removed), so it does not qualify as Destructive. The severity is medium because: (1) tags control behavior and membership in collections within Roblox, so incorrect tag application could alter game logic or performance; (2) an agent could mass-apply inappropriate tags across instances if given a broad path;…
From the tool's definition Tool adds a CollectionService tag to an instance, which modifies the instance's metadata state. The description explicitly states 'Add a CollectionService tag', indicating a reversible modification operation.
Attacks that exploit this kind of access
Add a CollectionService tag to an instance. Args: - path (string): Instance path - tag (string): Tag name Returns: Confirmation message. 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 add_tag: 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.
add_tag 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 add_tag 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 add_tag. 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.
add_tag 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 →