Medium Risk

add_folder

Add all files from a local folder as sources to a NotebookLM notebook. Use this when - User wants to add a folder of PDFs, docs, or text files to a notebook - Adding 5+ files at once (faster than calling add_source repeatedly) Behaviour - Scans the folder for supported file types (default: .pdf, ...

Risk signalsBulk/mass operation — affects multiple targets

Part of the Notebooklm server.

add_folder can modify Notebooklm data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE NOTEBOOKLM →

Free to start. No card required.

AI agents use add_folder to create or modify resources in Notebooklm. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call add_folder repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Notebooklm.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_folder": {
      "limits": [
        {
          "counter": "add_folder_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Notebooklm policy for all 68 tools.

Get this rule live on your own Notebooklm server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY NOTEBOOKLM →

View all 68 tools →

These attack patterns abuse exactly the kind of access add_folder gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so add_folder only ever does what you allow.

SECURE NOTEBOOKLM →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the add_folder tool do? +

Add all files from a local folder as sources to a NotebookLM notebook. Use this when - User wants to add a folder of PDFs, docs, or text files to a notebook - Adding 5+ files at once (faster than calling add_source repeatedly) Behaviour - Scans the folder for supported file types (default: .pdf, .txt, .md, .docx) - Adds each file one-by-one with progress updates - Skips files that fail and reports them in the summary - If file count exceeds your tier. It is categorised as a Write tool in the Notebooklm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_folder? +

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

What risk level is add_folder? +

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

Can I rate-limit add_folder? +

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

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

add_folder is provided by the Notebooklm MCP server (Pantheon-Security/notebooklm-mcp-secure). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Notebooklm tool call.

Deterministic rules across all 68 Notebooklm tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.