This record as markdown: /tools/cowork-os/canvas-close.md
What canvas_close does on CoWork OS
AI agents use canvas_close 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_close is rated Medium
Closing a canvas session terminates an active workflow state but is reversible (a new session can be created). This is a Write-category action—it modifies application state without permanent data loss or code execution. Severity is low because the blast radius is confined to the current session; no data is destroyed, no commands are executed, and the user can simply reopen a new canvas.
From the tool's definition Tool name 'canvas_close' with description 'Close a canvas session and its window' indicates state modification of an active session/window.
Attacks that exploit this kind of access
The rule that runs canvas_close 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_close, this is the rule to start with:
canvas_close 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_close call is checked against it from then on.
Questions about canvas_close
Close a canvas session and its window. 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_close: 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_close 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_close 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_close. 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_close 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