AI agents call get_entity_definition 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 read-only operation that extracts and returns information about entity definitions from Celeste map files. It does not modify, delete, or execute any code; it simply retrieves and parses existing metadata. The blast radius of misuse is minimal—an agent could request definitions repeatedly but cannot cause harm through this tool alone.
From the tool's definition Tool name 'get_entity_definition' and description 'Read a Lönn entity Lua definition and extract its properties' explicitly indicate retrieval of data with no side effects.
Attacks that exploit this kind of access
Read a Lönn entity Lua definition and extract its properties. 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 get_entity_definition: 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.
get_entity_definition 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 get_entity_definition 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 get_entity_definition. 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.
get_entity_definition 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 →