AI agents call read_map_metadata to retrieve information from Loenn without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves map metadata without creating, modifying, deleting, or executing code. It is a pure query operation with no side effects on the Celeste map file. The low severity reflects that reading metadata poses minimal risk even if an AI agent misuses it.
From the tool's definition Tool name and description explicitly state 'Read high-level metadata from a map' with no side effects mentioned. The verb 'read' and the constraint to metadata-only access without listing contents are standard read-only operations.
Attacks that exploit this kind of access
Read high-level metadata from a map without listing all room contents. It is categorised as a Read tool in the Loenn MCP Server, which means it retrieves data without modifying state.
Register the Loenn MCP server in PolicyLayer and add a rule for read_map_metadata: 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.
read_map_metadata is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_map_metadata 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 read_map_metadata. 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.
read_map_metadata 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.
read_map_metadata is one line of Loenn's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →