AI agents invoke pcg_skeleton_generate to trigger actions in Loenn. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The name suggests procedural content generation (PCG), which likely executes a generation algorithm to create or modify map content. Given the server's context of editing .bin map files and sibling tools that add rooms/entities, this tool likely generates map skeletons (Write/Execute level). With an empty description, confidence is lowered.
From the tool's definition Tool name 'pcg_skeleton_generate' and server description mentions 'procedurally generate' Celeste .bin map files; description is empty and uninformative.
Attacks that exploit this kind of access
pcg_skeleton_generate. It is categorised as a Execute tool in the Loenn MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Loenn MCP server in PolicyLayer and add a rule for pcg_skeleton_generate: 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.
pcg_skeleton_generate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the pcg_skeleton_generate 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 pcg_skeleton_generate. 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.
pcg_skeleton_generate 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 →