import_pack
AI agents use import_pack 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.
With no description provided, classification relies on naming conventions and server context. 'Import' typically means loading external data into a system (Write category). The sibling tools are predominantly Write operations (add_*, apply_*), confirming the server's data-modification focus. While the tool could theoretically overwrite existing campaign packs (Destructive), import operations are generally reversible.
From the tool's definition Tool name 'import_pack' suggests importing data into the system, consistent with sibling tools that modify character and campaign data (add_item_to_character, add_spell, add_event).
Attacks that exploit this kind of access
import_pack. 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 import_pack: 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.
import_pack 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 import_pack 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 import_pack. 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.
import_pack 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 →