This record as markdown: /tools/cowork-os/canvas-push.md
What canvas_push does on CoWork OS
AI agents use canvas_push to create or update resources in CoWork OS, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CoWork OS environment.
Why canvas_push is rated Medium
The tool writes/uploads HTML, CSS, and JavaScript content to a canvas session. This is a reversible write operation — content can be overwritten or removed. However, since it pushes executable JavaScript to a session, there is moderate risk if misused (e.g., injecting malicious scripts), but the primary action is a content write, not direct code execution in a broader system context.
From the tool's definition Push HTML/CSS/JS content to a canvas session
Attacks that exploit this kind of access
The rule that runs canvas_push safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For canvas_push, this is the rule to start with:
canvas_push stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every canvas_push call is checked against it from then on.
Questions about canvas_push
Push HTML/CSS/JS content to a canvas session. It is categorised as a Write tool in the CoWork OS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CoWork OS MCP server in PolicyLayer and add a rule for canvas_push: 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 CoWork OS. Nothing to install.
canvas_push 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 canvas_push 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_push. 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_push is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
This server
Across the catalogue