AI agents call analyze_room_connectivity 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 performs static analysis of map connectivity—extracting and reporting information about room relationships. It retrieves and presents data (adjacency graph, isolated rooms, dead ends, hubs) with no side effects or modifications to the map file. This is a pure Read operation, with low severity since misuse would only produce incorrect analysis without damaging the map or triggering external operations.
From the tool's definition Tool name 'analyze_room_connectivity' and description 'Analyze room adjacency graph showing isolated rooms, dead ends, and hubs' indicate a querying/analysis operation that examines map structure without modifying data.
Attacks that exploit this kind of access
Analyze room adjacency graph showing isolated rooms, dead ends, and hubs. 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 analyze_room_connectivity: 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.
analyze_room_connectivity 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 analyze_room_connectivity 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 analyze_room_connectivity. 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.
analyze_room_connectivity 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 →