Use a spell scroll in D&D 5e. If spell is on your class list and same/lower level: auto-success. If spell is higher level: Arcana check DC 10 + spell level. On failure: scroll is consumed with no effect. On success: spell is cast from scroll, scroll consumed.
AI agents invoke use_scroll to trigger actions in ChatRPG. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a game action (casting a spell from a scroll) that modifies game state — the scroll is consumed and the spell effect is applied. It is not purely reading data, nor does it delete persistent data irreversibly in a real-world sense; it operates within the RPG simulation context.
From the tool's definition 'Use a spell scroll in D&D 5e... spell is cast from scroll, scroll consumed' — triggers an in-game action with state changes (scroll consumed, spell cast)
Attacks that exploit this kind of access
Use a spell scroll in D&D 5e. If spell is on your class list and same/lower level: auto-success. If spell is higher level: Arcana check DC 10 + spell level. On failure: scroll is consumed with no effect. On success: spell is cast from scroll, scroll consumed. It is categorised as a Execute tool in the ChatRPG MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ChatRPG MCP server in PolicyLayer and add a rule for use_scroll: 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 ChatRPG. Nothing to install.
use_scroll is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the use_scroll 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 use_scroll. 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.
use_scroll is provided by the ChatRPG MCP server (mnehmos/mnehmos.chatrpg.game). 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 →