create_npc
AI agents use create_npc 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 creates new game entities (NPCs) within a D&D campaign context. Creation of reversible game data falls into the Write category. Severity is medium because misuse could clutter or degrade campaign data, but the effects are not destructive and are part of normal D&D gameplay. Confidence is reduced to 0.75 because the description is empty, requiring inference from context and naming convention.
From the tool's definition Tool name 'create_npc' indicates creation of a non-player character record. Based on sibling tools like 'add_item_to_character', 'add_spell', 'apply_effect', and 'add_event', the DM20 server manages game state including characters and game entities.
Attacks that exploit this kind of access
create_npc. 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 create_npc: 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.
create_npc 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_npc 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_npc. 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_npc 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 →