AI agents use upload_asset 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.
The upload_asset tool creates new assets in Roblox's system, representing a Write operation (reversible modification/creation of data). Severity is high because: (1) it requires API credentials or authentication tokens, creating exposure if misused; (2) uploading malicious assets (scripts, models, decals) could affect other users or projects in Roblox; (3) it consumes account quota and resource allocations.
From the tool's definition Tool explicitly performs 'Upload a local file as a Roblox asset', which is a create/modify operation that stores new data in Roblox's asset system.
Attacks that exploit this kind of access
Upload a local file as a Roblox asset via Open Cloud (API key) or, for Decals only, the legacy publish endpoint with a ROBLOSECURITY cookie. Auth: configure ~/.linkedsword/auth.json with {. 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 upload_asset: 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.
upload_asset 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 upload_asset 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 upload_asset. 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.
upload_asset 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 →