Register a library URL at the session level. The URL is persisted to disk so the browser auto-restores it on reload. Also validates by fetching the library once (count of items returned for confirmation).
AI agents use library_install 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.
This tool creates or modifies configuration state (library URL registration) that persists to disk. While not destructive (reversible via uninstall or reconfiguration) and not immediately dangerous, it commits external resources to the session. A malicious agent could register malicious library URLs, introducing supply-chain risks or trojaned drawing assets into the Excalidraw canvas.
From the tool's definition Tool description states it 'Register[s] a library URL at the session level' and 'persisted to disk', indicating creation/modification of persistent state. The validation fetch confirms a write operation occurs.
Attacks that exploit this kind of access
Register a library URL at the session level. The URL is persisted to disk so the browser auto-restores it on reload. Also validates by fetching the library once (count of items returned for confirmation). 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.
Register the Whiteboard MCP server in PolicyLayer and add a rule for library_install: 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.
library_install 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 library_install 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 library_install. 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.
library_install 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.
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 →