AI agents use import_svg 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 new document content (PenNodes) from an external file source, modifying the .op document irreversibly (the imported nodes become part of the document). This is a Write operation because it adds/modifies data reversibly within a document context, rather than being Execute (which would involve running arbitrary code) or Destructive (which would require deletion/overwrite of existing content).
From the tool's definition Tool description states it 'Import[s] a local SVG file into an .op document as editable PenNodes', which creates or modifies document structure by converting external SVG data into native document nodes.
Attacks that exploit this kind of access
Import a local SVG file into an .op document as editable PenNodes. Supports path, rect, circle, ellipse, line, polygon, polyline, and nested groups. No network access required. 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 import_svg: 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.
import_svg 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_svg 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_svg. 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_svg 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 →