AI agents use pcg_markov_fill 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.
This tool creates or modifies map data reversibly within a .bin file (procedural generation context), which is a Write operation. It does not delete or overwrite existing data irreversibly (not Destructive), does not execute arbitrary code (not Execute), and has no financial impact.
From the tool's definition Tool name 'pcg_markov_fill' suggests procedural content generation (PCG) using Markov chains to fill map data. Server description states the MCP enables agents to 'procedurally generate...Celeste .bin map files'.
Attacks that exploit this kind of access
pcg_markov_fill. 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 pcg_markov_fill: 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_markov_fill 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 pcg_markov_fill 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_markov_fill. 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_markov_fill 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 →