AI agents call export_object to retrieve information from Penpot MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads/exports an existing design object and renders it as an image. It retrieves data (a visual representation) without modifying, deleting, or executing anything. The blast radius is low as it only reads design content.
From the tool's definition Export a Penpot object as an image
Documented attack patterns abuse exactly the kind of access export_object gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Penpot MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for export_object:
{
"version": "1",
"default": "deny",
"tools": {
"export_object": {}
}
}export_object is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Export a Penpot object as an image. It is categorised as a Read tool in the Penpot MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Penpot MCP Server MCP server in PolicyLayer and add a rule for export_object: 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 Penpot MCP Server. Nothing to install.
export_object 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 export_object 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 export_object. 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.
export_object is provided by the Penpot MCP Server MCP server (montevive/penpot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Penpot MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Penpot MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.