AI agents invoke pcg_pipeline 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 'pcg_pipeline' strongly suggests a procedural content generation pipeline, which would execute a multi-step generation process to create or modify map data. Given the server's stated capability of procedural generation, this likely triggers complex operations with significant side effects on map files. However, the empty description lowers confidence — it could be Read or Write in nature.
From the tool's definition Tool name 'pcg_pipeline' on a server that 'procedurally generate' Celeste .bin map files; description is empty.
Attacks that exploit this kind of access
pcg_pipeline. 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_pipeline: 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_pipeline 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_pipeline 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_pipeline. 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_pipeline 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 →