Reload auth tokens from disk or run headless re-authentication.

Call this after running nlm login to pick up new tokens, or to attempt automatic re-authentication if Chrome profile has saved login.

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

Args: cookies: Cookie header from Chrome DevTools (only needed if CLI fails) csrf_token: Deprecated - auto-extracted session_id: Deprecated - auto-extracted request_body: Optional - contains CSRF if extracting manually request_url: Optional - contains session ID if extracting manually

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

Args: action: Operation to perform (query, add_source, create, delete, studio) query: Question to ask (for action=query) source_url: URL to add (for action=add_source) titles: Comma-separated notebook titles (for action=create) artifact_type: Artifact type (for action=studio): audio, video, report, etc. notebook_names: Comma-separated notebook names or IDs tags: Comma-separated tags to select notebooks all: Apply to ALL notebooks confirm: Must be True for delete action

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.

Args: notebook_id: Notebook UUID query: Question to ask source_ids: Source IDs to query (default: all) conversation_id: For follow-up questions timeout: Request timeout in seconds (default: from env NOTEBOOKLM_QUERY_TIMEOUT or 120.0) new_conversation: Start a fresh conversation when conversation_id is omitted

Configure notebook chat settings.

Args: notebook_id: Notebook UUID goal: default|learning_guide|custom custom_prompt: Required when goal=custom (max 10000 chars) response_length: default|longer|shorter

Start a notebook query asynchronously for large notebooks that may timeout.

Use this instead of notebook_query when querying notebooks with many sources (50+) where the response may take longer than 60 seconds. 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.

Args: notebook_id: Notebook UUID query: Question to ask source_ids: Source IDs to query (default: all) conversation_id: For follow-up questions timeout: Request timeout in seconds (default: from env NOTEBOOKLM_QUERY_TIMEOUT or 120.0) new_conversation: Start a fresh conversation when conversation_id is omitted

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'.

Args: query_id: The query ID returned by notebook_query_start

List chat sessions for a notebook.

Args: notebook_id: Notebook ID or title alias limit: Max chat sessions to return (default: 20)

Get full transcript of a specific chat session.

Args: notebook_id: Notebook ID or title alias conversation_id: Optional conversation ID (defaults to latest active session)

Export a chat transcript to Markdown or JSON.

Args: notebook_id: Notebook ID or title alias conversation_id: Optional conversation ID format: Export format: 'md' or 'json' (default: 'md')

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

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

Args: query: Question to ask across notebooks notebook_names: Comma-separated notebook names or IDs (e.g. "AI Research, Dev Tools") tags: Comma-separated tags to select notebooks (e.g. "ai,mcp") all: Query ALL notebooks (use with caution — rate limits apply)

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, quiz, flashcards.

Args: notebook_id: Notebook UUID artifact_type: Type of artifact to download: - audio: Audio Overview (MP4/MP3) - video: Video Overview (MP4) - report: Report (Markdown) - mind_map: Mind Map (JSON) - slide_deck: Slide Deck (PDF or PPTX) - infographic: Infographic (PNG) - data_table: Data Table (CSV) - quiz: Quiz (json|markdown|html) - flashcards: Flashcards (json|markdown|html) output_path: Path to save the file artifact_id: Optional specific artifact ID (uses latest if not provided) output_format: For quiz/flashcards only: json|markdown|html (default: json) slide_deck_format: For slide_deck only: pdf (default) or pptx wait: Poll while the artifact download is still propagating wait_timeout: Maximum seconds to wait when wait is enabled poll_interval: Seconds between readiness checks

Returns: dict with status and saved file path

Example: download_artifact(notebook_id="abc123", artifact_type="audio", output_path="podcast.mp3") download_artifact(notebook_id="abc123", artifact_type="quiz", output_path="quiz.html", output_format="html") download_artifact(notebook_id="abc123", artifact_type="slide_deck", output_path="slides.pptx", slide_deck_format="pptx")

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.

Args: notebook_id: Notebook UUID (omit when all_notebooks=True) output_dir: Base directory for the per-notebook folders (default: cwd) artifact_types: Restrict to these types, e.g. ["video", "slide_deck", "mind_map", "report"]. Default: all types. output_format: For quiz/flashcards only: json|markdown|html slide_deck_format: For slide decks only: pdf (default) or pptx all_notebooks: Sweep every notebook in the account instead of one skip_existing: Skip artifacts whose target file already exists — makes repeated runs incremental

Returns: dict with status, output_dir, and per-artifact items (single notebook) or per-notebook outcomes (sweep), plus downloaded/failed counts

Example: download_all_artifacts(notebook_id="abc123", output_dir="exports") download_all_artifacts(all_notebooks=True, output_dir="exports", skip_existing=True)

Export a NotebookLM artifact to Google Docs or Sheets.

Supports:

• Data Tables → Google Sheets

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

Args: notebook_id: Notebook UUID artifact_id: Artifact UUID to export export_type: "docs" or "sheets" title: Title for exported document (optional)

Returns: URL to the created Google Doc/Sheet

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

Args: notebook_id: Notebook UUID action: Operation to perform: - auto: AI auto-labels all sources into thematic categories - list: List current labels (triggers AI if none exist) - reorganize: Force AI re-categorization (requires confirm=True unless unlabeled_only=True) - create: Create a new empty label (requires name) - rename: Rename a label (requires label_id, name) - set_emoji: Set or clear emoji on a label (requires label_id, emoji) - move_source: Assign a source to a label (requires label_id, source_id) - delete: Delete label(s) permanently (requires label_id or label_ids, confirm=True) label_id: Label UUID (required for rename, set_emoji, move_source, delete) label_ids: List of label UUIDs for batch delete (alternative to label_id) name: Label display name (required for create and rename) emoji: Emoji character for set_emoji (e.g. "📊"), or "" to clear source_id: Source UUID to assign (required for move_source) unlabeled_only: For reorganize: if True, only label sources not yet in any label. If False (default), replaces ALL existing labels from scratch (requires confirm=True). confirm: Must be True for delete action and for reorganize with unlabeled_only=False

Returns: Action-specific response with status

Example: label(notebook_id="abc", action="auto") label(notebook_id="abc", action="list") label(notebook_id="abc", action="reorganize", confirm=True) label(notebook_id="abc", action="reorganize", unlabeled_only=True) label(notebook_id="abc", action="create", name="Research", emoji="📚") label(notebook_id="abc", action="rename", label_id="xyz", name="Better Name") label(notebook_id="abc", action="set_emoji", label_id="xyz", emoji="🎯") label(notebook_id="abc", action="move_source", label_id="xyz", source_id="src-id") label(notebook_id="abc", action="delete", label_id="xyz", confirm=True)

List all notebooks.

Args: max_results: Maximum number of notebooks to return (default: 100)

Get notebook details with sources.

Args: notebook_id: Notebook UUID

Get AI-generated notebook summary with suggested topics.

Args: notebook_id: Notebook UUID

Returns: summary (markdown), suggested_topics list

Create a new notebook.

Args: title: Optional title for the notebook

Rename a notebook.

Args: notebook_id: Notebook UUID new_title: New title

Delete notebook permanently. IRREVERSIBLE. Requires confirm=True.

Args: notebook_id: Notebook UUID confirm: Must be True after user approval

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

Supports: create, list, update, delete

Args: notebook_id: Notebook UUID action: Operation to perform: - create: Create a new note - list: List all notes in notebook - update: Update an existing note - delete: Delete a note permanently (requires confirm=True) note_id: Note UUID (required for update/delete) content: Note content (required for create, optional for update) title: Note title (optional for create/update) confirm: Must be True for delete action

Returns: Action-specific response with status

Example: note(notebook_id="abc", action="list") note(notebook_id="abc", action="create", content="My note", title="Title") note(notebook_id="abc", action="update", note_id="xyz", content="Updated") note(notebook_id="abc", action="delete", note_id="xyz", confirm=True)

Manage and execute multi-step notebook pipelines.

Actions:

• run: Execute a pipeline on a notebook

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

Args: action: Operation to perform (run, list) notebook_id: Target notebook UUID (required for action=run) pipeline_name: Pipeline name (required for action=run, e.g. "ingest-and-podcast") input_url: URL variable for pipelines that need it (replaces $INPUT_URL)

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.

Args: query: What to search for (e.g. "quantum computing advances") source: web|drive (where to search) mode: fast (~30s, ~10 sources) | deep (~5min, ~40 sources, web only) notebook_id: Existing notebook (creates new if not provided) title: Title for new notebook

Poll research progress. Blocks until complete or timeout.

Args: notebook_id: Notebook UUID poll_interval: Seconds between polls (default: 30) max_wait: Max seconds to wait (default: 900, 0=single poll) compact: If True (default), truncate report and limit sources shown to save tokens. Use compact=False to get full details. task_id: Optional Task ID to poll for a specific research task. query: Optional query text for fallback matching when task_id changes (deep research). Contributed by @saitrogen (PR #15). auto_import: If True, automatically import sources when research completes. If False (default), returns next_action hint to call research_import manually.

Import discovered sources into notebook.

Call after research_status shows status="completed".

Args: notebook_id: Notebook UUID task_id: Research task ID source_indices: Source indices to import (default: all) timeout: Import timeout in seconds (default: 300, increase for large notebooks) cited_only: Import only sources cited by the research report. Overrides source_indices when enabled.

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 - 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

Get current sharing settings and collaborators.

Args: notebook_id: Notebook UUID

Returns: is_public, access_level, collaborators list, and public_link if public

Enable or disable public link access.

Args: notebook_id: Notebook UUID is_public: True to enable public link, False to disable (default: True)

Returns: public_link if enabled, None if disabled

Invite a collaborator by email.

Args: notebook_id: Notebook UUID email: Email address to invite role: "viewer" or "editor" (default: viewer)

Returns: success status

Invite multiple collaborators in a single request.

Args: notebook_id: Notebook UUID recipients: List of dicts, each with 'email' (str) and optional 'role' (str). Role defaults to 'viewer'. Example: [{"email": "a@b.com", "role": "editor"}] confirm: Must be True after user approval

Returns: invited_count, recipients list, and message

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

Args: action: Operation to perform (add, remove, list, select) notebook_id: Notebook UUID (required for add, remove) tags: Comma-separated tags (required for add, remove; e.g. "ai,research,llm") notebook_title: Optional display title (for add) query: Search query (required for select; e.g. "ai mcp" or "ai,mcp")

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

Supports: url, text, drive, file

Args: notebook_id: Notebook UUID source_type: Type of source to add: - url: Web page or YouTube URL - text: Pasted text content - drive: Google Drive document - file: Local file upload. The canonical local-admission contract has 43 case-insensitive extensions. Admission does not guarantee provider processing success for an individual file. OFFICIAL_FILE_EXTENSIONS: .pdf, .txt, .md, .docx, .csv, .pptx, .epub, .avif, .bmp, .gif, .heic, .heif, .ico, .jp2, .jpe, .jpeg, .jpg, .png, .tif, .tiff, .webp, .3g2, .3gp, .aac, .aif, .aifc, .aiff, .amr, .au, .avi, .cda, .m4a, .mid, .mp3, .mp4, .mpeg, .ogg, .opus, .ra, .ram, .snd, .wav, .wma Image-bearing sources may feed Studio video generation's visual-crop pipeline; charts, photos, and diagrams may be extracted as on-screen aids. url: URL to add (for source_type=url) urls: List of URLs to add in bulk (for source_type=url, alternative to url) text: Text content to add (for source_type=text) title: Display title (for text sources) file_path: Local file path on the machine running the MCP server (for source_type=file). A path on a different client/agent host is not accessible to the server. document_id: Google Drive document ID (for source_type=drive) doc_type: Drive doc type: doc|slides|sheets|pdf (for source_type=drive) wait: If True, wait for source processing to complete before returning wait_timeout: Max seconds to wait if wait=True (default 120)

Example: source_add(notebook_id="abc", source_type="url", url="https://example.com") source_add(notebook_id="abc", source_type="url", urls=["https://a.com", "https://b.com"]) source_add(notebook_id="abc", source_type="url", url="https://example.com", wait=True) source_add(notebook_id="abc", source_type="file", file_path="/path/to/doc.pdf", wait=True) source_add(notebook_id="abc", source_type="file", file_path="/path/to/screenshot.png", wait=True)

List sources with types and Drive freshness status.

Use before source_sync_drive to identify stale sources.

Args: notebook_id: Notebook UUID skip_freshness: If True, skip per-source freshness checks for faster listing

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

Call source_list_drive first to identify stale sources.

Args: source_ids: Source UUIDs to sync confirm: Must be True after user approval

Rename a source in a notebook.

Args: notebook_id: Notebook UUID containing the source source_id: Source UUID to rename new_title: New display title for the source

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

Args: source_id: Source UUID to delete (single) source_ids: List of source UUIDs to delete (bulk, alternative to source_id) confirm: Must be True after user approval

Get AI-generated source summary with keyword chips.

Args: source_id: Source UUID

Returns: summary (markdown with bold keywords), keywords list

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.

Args: source_id: Source UUID wait: Poll until indexed content is available wait_timeout: Maximum seconds to wait when wait is enabled poll_interval: Seconds between readiness checks

Returns: content (str), title (str), source_type (str), char_count (int)

Create any NotebookLM studio artifact. Unified creation tool.

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

Args: notebook_id: Notebook UUID artifact_type: Type of artifact to create: - audio: Audio Overview (podcast) - video: Video Overview - infographic: Visual infographic - slide_deck: Presentation slides (PDF) - report: Text report (Briefing Doc, Study Guide, etc.) - flashcards: Study flashcards - quiz: Multiple choice quiz - data_table: Structured data table - mind_map: Visual mind map source_ids: Source IDs to use (default: all sources) confirm: Must be True after user approval

Type-specific options:
- audio: audio_format (deep_dive|brief|critique|debate), audio_length (short|default|long)
- video: video_format (explainer|brief|cinematic|short), visual_style (auto_select|custom|classic|whiteboard|kawaii|anime|watercolor|retro_print|heritage|paper_craft; not for cinematic/short), video_style_prompt
- infographic: orientation (landscape|portrait|square), detail_level (concise|standard|detailed), infographic_style (auto_select|sketch_note|professional|bento_grid|editorial|instructional|bricks|clay|anime|kawaii|scientific)
- slide_deck: slide_format (detailed_deck|presenter_slides), slide_length (short|default)
- report: report_format (Briefing Doc|Study Guide|Blog Post|Create Your Own), custom_prompt
- flashcards: difficulty (easy|medium|hard)
- quiz: question_count (int), difficulty (easy|medium|hard)
- data_table: description (required)
- mind_map: title

Common options:
- language: BCP-47 code (en, es, fr, de, ja). Defaults to NOTEBOOKLM_HL env var or 'en'
- focus_prompt: Optional focus text

Example: studio_create(notebook_id="abc", artifact_type="audio", confirm=True) studio_create(notebook_id="abc", artifact_type="quiz", question_count=5, confirm=True)

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

Args: notebook_id: Notebook UUID action: Action to perform: - status (default): List all artifacts with their status and URLs - rename: Rename an artifact (requires artifact_id and new_title) - list_types: List all supported artifact types with their options artifact_id: For status, return only this artifact. Required for action="rename". new_title: Required for action="rename" - the new title for the artifact include_details: Include prompts, source IDs, report content, and media details limit: Maximum artifacts to return for status (1-100, default 20) offset: Number of artifacts to skip for status pagination

Returns: Dictionary with status and results. For action="status": - status: "success" - artifacts: Lean page of artifacts, each containing: - artifact_id: UUID - title: Artifact title - type: audio, video, report, etc. - status: completed, in_progress, failed - created_at: Creation timestamp - error_reason: Failure guidance when status is failed With include_details=True, artifacts also include prompts, source IDs, report content, media URLs, and other rich fields. - summary: Counts of total, completed, in_progress - pagination: returned, offset, limit, and has_more

Delete studio artifact. IRREVERSIBLE. Requires confirm=True.

Args: notebook_id: Notebook UUID artifact_id: Artifact UUID (from studio_status) confirm: Must be True after user approval

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.

Args: notebook_id: Notebook UUID artifact_id: UUID of the existing slide deck to revise (from studio_status) slide_instructions: List of revision instructions, each with: - slide: Slide number (1-based, slide 1 = first slide) - instruction: Text describing the desired change Example: [{"slide": 1, "instruction": "Make the title larger"}] confirm: Must be True after user approval

Example: studio_revise( notebook_id="abc", artifact_id="xyz", slide_instructions=[ {"slide": 1, "instruction": "Make the title larger"}, {"slide": 3, "instruction": "Remove the image"} ], confirm=True )