update_character
AI agents use update_character to create or update resources in DM20 Protocol — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DM20 Protocol environment.
This tool modifies character game state (attributes, inventory, abilities, or statistics) but does not irreversibly delete data or execute arbitrary code. Changes to D&D character sheets are reversible through subsequent updates. Severity is medium due to potential for disruption of gameplay if a character is modified maliciously, but impact is limited to a single character record in a game context.
From the tool's definition Tool name 'update_character' combined with sibling tools 'add_item_to_character', 'add_spell', 'apply_effect', and 'approve_sheet_change' indicate character sheet modification operations.
Attacks that exploit this kind of access
update_character. It is categorised as a Write tool in the DM20 Protocol MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DM20 Protocol 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 DM20 Protocol. 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 DM20 Protocol MCP server (polloinfilzato/dm20-protocol). 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 →