This record as markdown: /tools/openclaw/canvas.md
What canvas does on OpenClaw
AI agents call canvas to retrieve information from OpenClaw without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why canvas is rated Low
The tool captures or renders canvas content, which primarily suggests a read/retrieval operation. However, 'render' could imply triggering a computation or side effect. The description is sparse and the server has no overall description, lowering confidence. Classified as Read at medium severity since canvas content could include sensitive visual data.
From the tool's definition 'Capture or render canvas content from a paired node' — 'capture' suggests reading/retrieving content; 'render' is ambiguous but likely implies displaying/retrieving visual output
Attacks that exploit this kind of access
The rule that runs canvas safely
PolicyLayer is an MCP gateway: it sits between your AI agents and OpenClaw, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For canvas, this is the rule to start with:
canvas 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 OpenClaw, apply this rule, and every canvas call is checked against it from then on.
Questions about canvas
Capture or render canvas content from a paired node. It is categorised as a Read tool in the OpenClaw MCP Server, which means it retrieves data without modifying state.
Register the OpenClaw MCP server in PolicyLayer and add a rule for 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 OpenClaw. Nothing to install.
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 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 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.
canvas is provided by the OpenClaw MCP server (openclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on OpenClaw, and thousands of servers like it.
This server
Across the catalogue