AI agents use set_variables to create or update resources in Pen — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pen environment.
This tool creates or modifies data (design variables) reversibly. It does not execute arbitrary code, delete data, or move money. The scope is confined to variable definitions within a document, making the blast radius medium if misused (e.g., corrupting design settings), but changes can be undone.
From the tool's definition Tool description states 'Add or update design variables in an .op file' — these are write operations that modify document state.
Attacks that exploit this kind of access
Add or update design variables in an .op file. By default merges with existing variables. It is categorised as a Write tool in the Pen MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pen MCP server in PolicyLayer and add a rule for set_variables: 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 Pen. Nothing to install.
set_variables 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 set_variables 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 set_variables. 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.
set_variables is provided by the Pen MCP server (@zseven-w/pen-mcp). 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 →