canvas_checkpoint
Save a named checkpoint of the current canvas state.
This record as markdown: /tools/cowork-os/canvas-checkpoint.md
What canvas_checkpoint does on CoWork OS
AI agents use canvas_checkpoint 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_checkpoint is rated Medium
Saving a checkpoint is a write operation as it creates new data (a named snapshot). It is reversible and localized to canvas state management with minimal blast radius, hence low severity. The description is clear and direct, supporting high confidence.
From the tool's definition Tool description explicitly states 'Save a named checkpoint' — this is a create operation that stores a canvas state snapshot. It is reversible (checkpoints can be overwritten or deleted) and has no destructive or external side effects.
Attacks that exploit this kind of access
The rule that runs canvas_checkpoint 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_checkpoint, this is the rule to start with:
canvas_checkpoint 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_checkpoint call is checked against it from then on.
Questions about canvas_checkpoint
Save a named checkpoint of the current canvas state. 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_checkpoint: 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_checkpoint 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_checkpoint 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_checkpoint. 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_checkpoint 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