version_save

Save a labeled version of the canvas state. Returns versionId for later restore. Versions are slug-scoped (canvas-local) and auto-pruned per-canvas, replacing the prior checkpoint flow.

Server Whiteboard kamiazya/whiteboard
Category Write
Risk class Medium
Parameters 00 required

What version_save does on Whiteboard

AI agents use version_save to create or update resources in Whiteboard — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Whiteboard environment.

Why version_save needs a policy

The tool creates and stores labeled checkpoints of canvas state. While it involves persisting data (a Write operation), the versions are scoped and auto-pruned rather than directly modifying user documents. It is reversible because versions can be restored later and old versions are replaced, not destructively purged.

From the tool's definition 'Save a labeled version of the canvas state' with 'versionId for later restore' indicates creating and storing new canvas state snapshots that can be retrieved later.

Questions about version_save

What does the version_save tool do? +

Save a labeled version of the canvas state. Returns versionId for later restore. Versions are slug-scoped (canvas-local) and auto-pruned per-canvas, replacing the prior checkpoint flow. It is categorised as a Write tool in the Whiteboard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on version_save? +

Register the Whiteboard MCP server in PolicyLayer and add a rule for version_save: 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 Whiteboard. Nothing to install.

What risk level is version_save? +

version_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit version_save? +

Yes. Add a rate_limit block to the version_save 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.

How do I block version_save completely? +

Set action: deny in the PolicyLayer policy for version_save. 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.

What MCP server provides version_save? +

version_save is provided by the Whiteboard MCP server (kamiazya/whiteboard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.