31 tools. 16 can modify or destroy data without limits.
5 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (re_auth, remove_notebook, remove_source) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (add_notebook, add_source, batch_create_notebooks) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Intercept sits between your agent and Notebooklm. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @pan-sec/notebooklm-mcp re_auth:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
add_notebook:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
ask_question:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Notebooklm server exposes 5 destructive tools including re_auth, remove_notebook, remove_source. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Notebooklm server has 11 write tools including add_notebook, add_source, batch_create_notebooks. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
31 tools across 3 categories: Destructive, Read, Write. 15 are read-only. 16 can modify, create, or delete data.
One line change. Instead of running the Notebooklm server directly, prefix it with Intercept: intercept -c io-github-pantheon-security-notebooklm-mcp-secure.yaml -- npx -y @@pan-sec/notebooklm-mcp. Download a pre-built policy from policylayer.com/policies/io-github-pantheon-security-notebooklm-mcp-secure and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init