Take a PNG screenshot of the current canvas and return it as a base64 image.
AI agents call get_canvas_screenshot to retrieve information from tldraw MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshot capture is a read-only operation that retrieves the current state of the canvas without side effects. It does not create, modify, delete, or execute any operations. The base64 return format is simply data serialization for transmission. This poses minimal risk as it only exposes what is already visible on the canvas.
From the tool's definition Tool description states it 'Take[s] a PNG screenshot of the current canvas and return[s] it as a base64 image.' This retrieves visual data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Take a PNG screenshot of the current canvas and return it as a base64 image. It is categorised as a Read tool in the tldraw MCP Server MCP Server, which means it retrieves data without modifying state.
Register the tldraw MCP Server MCP server in PolicyLayer and add a rule for get_canvas_screenshot: 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.
get_canvas_screenshot 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 get_canvas_screenshot 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 get_canvas_screenshot. 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.
get_canvas_screenshot 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 →