AI agents use update_character to create or update resources in ChatRPG — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ChatRPG environment.
This tool creates or modifies character game state reversibly. Changes to character attributes can be undone by subsequent updates or restoration, making it Write rather than Destructive. The impact is scoped to a single character's data within a game context, limiting the blast radius to medium severity.
From the tool's definition Tool name 'update_character' and description 'Update an existing D&D 5e character with new stats, HP, level, equipment, etc.' indicate modification of character data.
Attacks that exploit this kind of access
Update an existing D&D 5e character with new stats, HP, level, equipment, etc. It is categorised as a Write tool in the ChatRPG MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ChatRPG MCP server in PolicyLayer and add a rule for update_character: 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.
update_character 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 update_character 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 update_character. 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.
update_character 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 →