Import elements from a JSON string (from export_scene).
AI agents use import_scene to create or update resources in tldraw MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your tldraw MCP Server environment.
Importing elements is a reversible write operation—it adds or modifies diagram data on the canvas without permanently destroying existing content. While it could overwrite existing elements depending on implementation, the description suggests it processes JSON input to populate the scene. This is less severe than Destructive (no explicit deletion) but more impactful than a Read operation.
From the tool's definition Tool description states it 'Import elements from a JSON string', which creates/adds elements to the canvas. The tldraw context confirms this modifies the visual state of a live canvas.
Attacks that exploit this kind of access
Import elements from a JSON string (from export_scene). It is categorised as a Write tool in the tldraw MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the tldraw MCP Server MCP server in PolicyLayer and add a rule for import_scene: 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 tldraw MCP Server. Nothing to install.
import_scene 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_scene 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_scene. 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_scene is provided by the tldraw MCP Server MCP server (mihai-codes/tldraw-mcp-server). 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 →