get_npc
AI agents call get_npc to retrieve information from DM20 Protocol without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_npc' tool appears to be a read-only data retrieval operation for Non-Player Character records within a D&D campaign management system. Even without explicit documentation, the naming convention and server context indicate this retrieves existing game data rather than modifying, deleting, or executing external operations.
From the tool's definition Tool name 'get_npc' indicates retrieval of Non-Player Character data; no description provided but naming convention and context (D&D campaign management server with character sheets and world-building) strongly suggests a query operation that retrieves NPC…
Attacks that exploit this kind of access
get_npc. It is categorised as a Read tool in the DM20 Protocol MCP Server, which means it retrieves data without modifying state.
Register the DM20 Protocol MCP server in PolicyLayer and add a rule for get_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.
get_npc is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_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 →