AI agents use set_attribute 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 or modifies attributes on Roblox instances reversibly. It is a Write operation because attributes can be changed back or reverted. While it modifies state within Roblox Studio, the change is not destructive and does not execute arbitrary code or delete data. Severity is medium because misuse could corrupt game logic or instance configuration, but changes are reversible.
From the tool's definition Tool description states 'Set an attribute on an instance' with args for path, name, and value. Returns confirmation with old and new values, indicating modification of existing data.
Attacks that exploit this kind of access
Set an attribute on an instance. Args: - path (string): Instance path - name (string): Attribute name - value (any): Attribute value Returns: Confirmation with old and new values. 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 set_attribute: 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.
set_attribute 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 set_attribute 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 set_attribute. 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.
set_attribute 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 →