Return all shapes currently on the canvas. Call this before edits to know what
AI agents call get_canvas to retrieve information from Tl Draw without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves canvas state without modifying, executing code, or creating side effects. It is a straightforward query operation that reads the current state of a drawing canvas. The lower severity reflects minimal blast radius—misuse would only expose drawing data, not cause harm.
From the tool's definition Tool name is 'get_canvas' and description states it will 'Return all shapes currently on the canvas' with no mention of modification, deletion, or side effects.
Documented attack patterns abuse exactly the kind of access get_canvas gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tl Draw, and nothing reaches the server without passing your rules. This is the rule we recommend for get_canvas:
{
"version": "1",
"default": "deny",
"tools": {
"get_canvas": {}
}
}get_canvas 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.
Return all shapes currently on the canvas. Call this before edits to know what. It is categorised as a Read tool in the Tl Draw MCP Server, which means it retrieves data without modifying state.
Register the Tl Draw MCP server in PolicyLayer and add a rule for get_canvas: 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 Tl Draw. Nothing to install.
get_canvas 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 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. 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 is provided by the Tl Draw MCP server (siddharth11roy/tldraw-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tl Draw, 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.
4 Tl Draw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.