AI agents call get_asset_details 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.
The tool retrieves asset metadata from Roblox by ID. It performs no side effects, does not modify state, execute code, or handle financial operations. The public nature of the endpoint and lack of authentication requirements further confirm this is a simple read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Fetch metadata' which is a read-only operation. Accessing a 'Public endpoint' with 'no auth required' confirms this is a data retrieval operation.
Attacks that exploit this kind of access
Fetch metadata for a Roblox asset by id. Public endpoint, no auth required. Args: - assetId (number) Returns: Raw asset details payload. 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_asset_details: 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_asset_details 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_asset_details 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_asset_details. 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_asset_details 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 →