AI agents use create_quest to create or update resources in Idelrpg — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Idelrpg environment.
This tool creates new quest records in a local game state system. It modifies the game's data store by adding entries, which is a Write operation. The severity is medium because misuse could corrupt the quest system or flood it with invalid quests, but the impact is limited to a single user's local game state and the data structure is designed to accommodate quests.
From the tool's definition Tool description states 'Create an IDEL RPG quest' — the verb 'create' indicates data creation. The quest is 'stored locally' per server description, making it a reversible write operation that can be modified or deleted later.
Attacks that exploit this kind of access
Create an IDEL RPG quest with done criteria and a validation command. It is categorised as a Write tool in the Idelrpg MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Idelrpg MCP server in PolicyLayer and add a rule for create_quest: 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 Idelrpg. Nothing to install.
create_quest is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_quest 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 create_quest. 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.
create_quest is provided by the Idelrpg MCP server (jrslyce/idelrpg). 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 →