Manage aliases: short names that stand in for notebook IDs.

Once an alias exists, any tool's notebook_id can be the alias. Aliases are shared across all profiles.

Reload auth for the requested profile without switching the active account.

Call this after running nlm login to pick up new tokens, or attempt headless recovery with the profile's saved browser. An explicit profile does not switch the MCP server's active account.

Returns status indicating if tokens were refreshed successfully.

Save NotebookLM cookies (FALLBACK method - try nlm login first!).

IMPORTANT FOR AI ASSISTANTS:

• First, run nlm login via Bash/terminal (automated, preferred)

• Only use this tool if the automated CLI fails

Perform batch operations across multiple notebooks.

Actions:

• query: Query multiple notebooks with the same question

• add_source: Add the same source URL to multiple notebooks

• create: Create multiple notebooks at once

• delete: Delete multiple notebooks (IRREVERSIBLE, requires confirm=True)

• studio: Generate studio artifacts across multiple notebooks

Ask AI about EXISTING sources already in notebook. NOT for finding new sources.

Use research_start instead for: deep research, web search, find new sources, Drive search.

Configure notebook chat settings.

Start a notebook query asynchronously for source-heavy notebooks or long questions.

Use this instead of notebook_query when the response may take longer than the default 120-second budget. A timeout around 180 seconds is a useful starting point for source-heavy notebooks. Returns immediately with a query_id. Poll notebook_query_status with the query_id to get the result.

Workflow: notebook_query_start -> poll notebook_query_status until completed.

Check the status of an async notebook query started with notebook_query_start.

Returns the query result when completed, or current status if still in progress. Poll this tool every few seconds until status is 'completed' or 'error'.

List chat sessions for a notebook.

Get full transcript of a specific chat session.

Export a chat transcript to Markdown or JSON.

Save a chat (or one turn of it) as a Note in the notebook.

Permanently delete all chat history for a notebook. Requires confirmation.

List all native collections.

Create a new collection.

Edit an existing collection's name and/or list of notebooks.

Set or clear the emoji marker on a collection.

Delete a collection permanently. Notebooks inside the collection are NOT deleted.

Query multiple notebooks and get aggregated answers with per-notebook citations.

Specify notebooks by name, by tags, or use all=True for all notebooks.

Download any NotebookLM artifact to a file.

Unified download tool replacing 9 separate download tools. Supports all artifact types: audio, video, report, mind_map, slide_deck, infographic, data_table, file, quiz, flashcards.

Download all completed studio artifacts of one notebook — or every notebook.

Creates a subdirectory of output_dir named after each notebook title and saves every completed artifact there, named after its title with the type's default extension (report → .md, mind_map → .json, video → .mp4, slide_deck → .pdf/.pptx, ...). Artifacts that are still generating or failed are skipped and listed in the result. A failure on one artifact (or one notebook in a sweep) does not stop the others.

Export a NotebookLM artifact to Google Docs or Sheets.

Supports:

• Data Tables → Google Sheets

• Reports (Briefing Doc, Study Guide, Blog Post) → Google Docs

Manage source labels in a notebook. Unified tool for all label operations.

Labels let you organize sources into thematic categories. Requires 5+ sources for auto-labeling. Sources can belong to multiple labels simultaneously.

Supports: auto, list, reorganize, create, rename, set_emoji, move_source, delete

List all notebooks.

Get notebook details with sources.

Get AI-generated notebook summary with suggested topics.

Create a new notebook.

Rename a notebook.

Delete notebook permanently. IRREVERSIBLE. Requires confirm=True.

Manage notes in a notebook. Unified tool for all note operations.

Supports: create, list, update, delete

Manage and execute multi-step notebook pipelines.

Actions:

• run: Execute a pipeline on a notebook

• list: List all available pipelines (builtin and user-defined)

• create: Save a user-defined pipeline (pipeline_name + steps; each step is {"action": , "params": {...}})

List saved Google accounts (profiles) and choose which one to use.

Deep research / fast research: Search web or Google Drive to FIND NEW sources.

Use this for: "deep research on X", "find sources about Y", "search web for Z", "search Drive". Workflow: research_start -> poll research_status -> research_import.

Poll research progress. Blocks until complete or timeout.

Import discovered sources into notebook.

Call after research_status shows status="completed".

Get version, auth status, and conservative MCP capability visibility.

AI assistants: If update_available is True, inform the user that a new version is available and suggest updating with the provided command.

auth_status is the result of an AuthHealthChecker probe. The checker runs a multi-probe strategy (homepage fetch + API fallback) with 30-second TTL caching and mtime-based bypass on auth-file changes. The reported value may therefore be up to 30 seconds old, and an external nlm login is picked up within one check cycle without waiting for the TTL to expire.

auth_status meanings:

• "configured" — homepage (or API fallback) check passed; credentials are good. Cached credentials may be reported as configured for up to 30 seconds.

• "not_configured" — no credentials are stored (first-time setup).

• "stale" — credentials are known-bad (expired or past the 7-day heuristic). Operations will fail; ask the user to run nlm login to refresh.

• "unverified" — the check could not be completed (network error, timeout, non-200 response). Cached credentials may still work for actual API calls, so do not assume the user needs to re-auth.

• "error" — unexpected exception inside the check itself.

Returns: dict with version info: - version: Current installed version - latest_version: Latest version on PyPI (or None if check failed) - update_available: True if a newer version is available - auth_status: configured | stale | unverified | not_configured | error - storage_warning: Short warning if conflict/pending op exists (or None) - update_command: Command to run to update - mcp_capabilities: Built-in tool groups visible in this server process - provider_capabilities: Explicitly unprobed provider/account capabilities

• active_profile: Which saved account is in use and why (session switch or saved default)

• profiles: Saved accounts with email, storage mode (plain/protected) and any storage problems. Metadata only; never opens the OS keystore.

Get current sharing settings and collaborators.

Enable or disable public link access.

Invite a collaborator by email.

Invite multiple collaborators in a single request.

Manage notebook tags and find relevant notebooks by tag matching.

Actions:

• add: Add tags to a notebook for smart selection

• remove: Remove tags from a notebook

• list: List all tagged notebooks with their tags

• select: Find notebooks relevant to a query using tag matching

Add a source to a notebook. Unified tool for all source types.

Supports: url, text, drive, file

List sources with types and Drive freshness status.

Use before source_sync_drive to identify stale sources. Returned Drive sources include can_sync to identify files eligible for a manual Drive sync attempt. An individual sync attempt may still fail.

Sync Drive sources with latest content. Requires confirm=True.

Call source_list_drive first to identify stale sources.

Rename a source in a notebook.

Delete source(s) permanently. IRREVERSIBLE. Requires confirm=True.

Get AI-generated source summary with keyword chips.

Get raw text content of a source (no AI processing).

Returns the original indexed text from PDFs, web pages, pasted text, or YouTube transcripts. Much faster than notebook_query for content export.

Create any NotebookLM studio artifact. Unified creation tool.

Supports: audio, video, infographic, slide_deck, report, flashcards, quiz, data_table, mind_map

Check studio content generation status and get URLs, or rename an artifact.

Work with an interactive report's embedded elements. Unified report tool.

Create the report itself with studio_create(artifact_type="report", report_format="Interactive"). Then:

Delete studio artifact. IRREVERSIBLE. Requires confirm=True.

Revise individual slides in an existing slide deck. Creates a NEW artifact.

Only slide decks support revision. The original artifact is not modified. Poll studio_status after calling to check when the new deck is ready.

Show how much of the plan's usage allowance is left, and when it resets.

Gemini Notebook meters usage as compute against two windows at once: a short rolling window and a weekly one. Both are reported, each with the percentage used, the percentage remaining and the reset time in UTC.

Search relevant indexed passages within one NotebookLM notebook (read-only).

Optional source_ids restrict retrieval to sources belonging to this notebook. Returns at most 20 excerpted passages with native source UUIDs and titles. No Gemini or Opal credentials are used. Experimental, off by default.

Set NOTEBOOKLM_ENABLE_NATIVE_SOURCE_SEARCH=1 in the server environment.