AI agents call kotor_describe_jrl to retrieve information from KotorMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and summarizes journal data from a Knights of the Old Republic game installation without making any changes. It is purely informational, fitting the Read category (retrieves or queries data; no side effects). The risk is minimal as it only exposes game state inspection capabilities with no ability to modify game data, execute code, or affect external systems.
From the tool's definition Tool name 'kotor_describe_jrl' and description explicitly states 'JRL (journal) summary: categories and entries. Read-only.' The description explicitly marks this as read-only, indicating no modifications or side effects.
Attacks that exploit this kind of access
Use when you need a JRL (journal) summary: categories and entries. Read-only. It is categorised as a Read tool in the KotorMCP MCP Server, which means it retrieves data without modifying state.
Register the Kotor MCP server in PolicyLayer and add a rule for kotor_describe_jrl: 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 KotorMCP. Nothing to install.
kotor_describe_jrl 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 kotor_describe_jrl 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 kotor_describe_jrl. 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.
kotor_describe_jrl is provided by the Kotor MCP server (th3w1zard1/kotormcp). 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 →