user_library_save · Whiteboard MCP: Risk & Policy

WHAT IT DOES

What user_library_save does on Whiteboard

AI agents use user_library_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 IT NEEDS A POLICY

Why user_library_save needs a policy

This tool writes data to disk at a user-accessible filesystem location. While not destructive (overwriting a library file is reversible if backups exist, and the operation is not a hard delete), it modifies persistent state.

From the tool's definition 'Save a user-level library to ~/.excalidraw/.user-libraries/{name}.excalidrawlib'; 'Same name overwrites' indicates the tool creates or modifies files persistently in the user's home directory.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

user_library_save Rate-limited

user_library_save 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "user_library_save": {
      "limits": [
        {
          "counter": "user_library_save_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Whiteboard, so you can run agents against it safely.

FAQ

Questions about user_library_save

What does the user_library_save tool do? +

Save a user-level library to ~/.excalidraw/.user-libraries/{name}.excalidrawlib. Provide EITHER fromUrl (fetched and stored) OR content (raw .excalidrawlib JSON object). Same name overwrites. The saved library is usable via userLibraryName in library_list_items / library_insert_item across sessions. 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 user_library_save? +

Register the Whiteboard MCP server in PolicyLayer and add a rule for user_library_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 user_library_save? +

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

Can I rate-limit user_library_save? +

Yes. Add a rate_limit block to the user_library_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 user_library_save completely? +

Set action: deny in the PolicyLayer policy for user_library_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 user_library_save? +

user_library_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.