This record as markdown: /tools/io-github-portel-dev-ncp/export-design.md
What export_design does on Ncp
AI agents call export_design to retrieve information from Ncp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why export_design is rated Low
Exporting a design is a read-like operation that produces a copy of existing data without modifying the source. However, depending on the export destination and permissions, it could expose sensitive design IP or trigger external file writes. Classified as Read since the primary action is retrieving/rendering existing data. Severity is medium because design exports can expose proprietary creative assets.
From the tool's definition 'Export Canva design' — exporting retrieves/serializes existing design data into a file format, with no indication of modification or deletion.
Attacks that exploit this kind of access
The rule that runs export_design safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For export_design, this is the rule to start with:
export_design is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every export_design call is checked against it from then on.
Questions about export_design
Export Canva design. It is categorised as a Read tool in the Ncp MCP Server, which means it retrieves data without modifying state.
Register the Ncp MCP server in PolicyLayer and add a rule for export_design: 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 Ncp. Nothing to install.
export_design 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_design 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_design. 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_design is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue