Export the current canvas to .excalidraw JSON format. Optionally write to a file.
AI agents call export_scene to retrieve information from Excalidraw MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The primary action is exporting/reading the canvas state to JSON format. The optional file write is a side effect, but the tool's core purpose is to retrieve and serialize the current scene data. Since it can write to a file, Write could apply, but the export/read semantic dominates and file writing is optional. Elevating to Write due to the optional file write capability.
From the tool's definition Export the current canvas to .excalidraw JSON format. Optionally write to a file.
Attacks that exploit this kind of access
Export the current canvas to .excalidraw JSON format. Optionally write to a file. It is categorised as a Read tool in the Excalidraw MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Excalidraw MCP Server MCP server in PolicyLayer and add a rule for export_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 Excalidraw MCP Server. Nothing to install.
export_scene 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_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 export_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.
export_scene is provided by the Excalidraw MCP Server MCP server (kakacoding1/mcp_excalidraw). 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 →