AI agents call get_selection to retrieve information from Melo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the current selection state from the Roblox Studio UI without modifying any data, triggering any operations, or causing side effects. It is a straightforward query operation that falls squarely into the Read category. Severity is low because reading selection state poses minimal risk—an AI agent cannot cause damage by querying what is currently selected.
From the tool's definition Tool description states 'Get the instances currently selected in the Studio Explorer panel' and 'Returns: Array of selected instance paths and classNames.' The verb 'Get' and the read-only return of selection state indicate no data modification or side…
Attacks that exploit this kind of access
Get the instances currently selected in the Studio Explorer panel. Returns: Array of selected instance paths and classNames. It is categorised as a Read tool in the Melo MCP Server, which means it retrieves data without modifying state.
Register the Melo MCP server in PolicyLayer and add a rule for get_selection: 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.
get_selection is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_selection 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 get_selection. 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.
get_selection 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 →