AI agents call find_entity_references 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 a lookup or search operation across map data to locate entities of a specific type. It has no side effects, creates no data, executes no code, and makes no destructive changes. It is a pure read operation analogous to a search or filter function. The low severity reflects minimal blast radius even if an AI agent misuses it—at worst, it returns unwanted information about map contents.
From the tool's definition Tool name 'find_entity_references' and description 'Find all occurrences of an entity type across the map' indicate a search/query operation that retrieves information without modifying data.
Attacks that exploit this kind of access
Find all occurrences of an entity type across the map. 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 find_entity_references: 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.
find_entity_references 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 find_entity_references 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 find_entity_references. 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.
find_entity_references 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 →