AI agents use update_styleground to create or update resources in Loenn — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Loenn environment.
Stylegrounds are visual/atmospheric elements in Celeste maps. Updating them modifies map data reversibly (edits can be undone by reloading or further edits), making this a Write operation rather than Destructive. The empty description lowers confidence slightly, but the name and server context are clear.
From the tool's definition Tool name 'update_styleground' indicates modification of styleground elements in Celeste map files. The server explicitly states it enables users to 'edit' .bin map files.
Attacks that exploit this kind of access
update_styleground. It is categorised as a Write tool in the Loenn MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Loenn MCP server in PolicyLayer and add a rule for update_styleground: 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 Loenn. Nothing to install.
update_styleground 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 update_styleground 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 update_styleground. 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.
update_styleground is provided by the Loenn MCP server (magedeline/loenn-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 →