notebooklm_source_add · Notebooklm Codex MCP: Risk & Policy

WHAT IT DOES

What notebooklm_source_add does on Notebooklm Codex

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

WHY IT NEEDS A POLICY

Why notebooklm_source_add needs a policy

This tool modifies notebook state by appending new sources, which is a Write operation (reversible data creation). Severity is medium because adding sources could introduce malicious or sensitive content into a notebook, potentially affecting downstream analysis or sharing, but the action itself is not destructive and can be undone by removing sources.

From the tool's definition Tool description states 'Add a URL, YouTube URL, or local file as a source to the active notebook' — this creates new source records within a user's notebook, a reversible modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

notebooklm_source_add Rate-limited

notebooklm_source_add 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": {
    "notebooklm_source_add": {
      "limits": [
        {
          "counter": "notebooklm_source_add_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 Notebooklm Codex, so you can run agents against it safely.

FAQ

Questions about notebooklm_source_add

What does the notebooklm_source_add tool do? +

Add a URL, YouTube URL, or local file as a source to the active notebook. It is categorised as a Write tool in the Notebooklm Codex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on notebooklm_source_add? +

Register the Notebooklm Codex MCP server in PolicyLayer and add a rule for notebooklm_source_add: 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 Notebooklm Codex. Nothing to install.

What risk level is notebooklm_source_add? +

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

Can I rate-limit notebooklm_source_add? +

Yes. Add a rate_limit block to the notebooklm_source_add 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 notebooklm_source_add completely? +

Set action: deny in the PolicyLayer policy for notebooklm_source_add. 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 notebooklm_source_add? +

notebooklm_source_add is provided by the Notebooklm Codex MCP server (knowingdoing/notebooklm-codex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.