{"report":{"v":1,"package":"notebooklm-mcp","version":"2.0.0","ranAt":"2026-11-16T11:30:14.829Z","install":{"ok":true,"integrity":"sha512-7OGz3A1MKLmQHcHx448hYzYaOwjpGehM0VC0VH+5QmHuUQDSNtGOXWnJB+0Cr3x1M5uRip3A+qy4q6cIRY0qWA==","deps":123,"scripts":[],"bins":["notebooklm-mcp"],"license":"MIT","engines":"node >=18.0.0","repository":"git+https://github.com/PleasePrompto/notebooklm-mcp.git","bin":"notebooklm-mcp"},"start":{"ok":true,"ms":393,"serverName":"notebooklm-mcp","serverVersion":"2.0.0","protocol":"2025-06-18","stderr":"f all server data on disk (auth state, browser profiles,...[0m\n[36mℹ️  [11:30:19]   - add_source: Ingest a source into a NotebookLM notebook. Supports two source types in v2.0:...[0m\n[36mℹ️  [11:30:19]   - generate_audio: Trigger podcast-style Audio Overview generation for a notebook....[0m\n[36mℹ️  [11:30:19]   - get_audio_status: Non-blocking probe for the current Audio Overview state of a notebook....[0m\n[36mℹ️  [11:30:19]   - download_audio: Save the completed Audio Overview to disk as a `.m4a` file. **Pre-condition:** `...[0m\n[36mℹ️  [11:30:19] [0m\n[36mℹ️  [11:30:19] 📖 For documentation, see: README.md[0m\n[36mℹ️  [11:30:19] [0m\n[36mℹ️  [11:30:19] 📋 [MCP] list_tools request received[0m\n[36mℹ️  [11:30:22] 🔧 [MCP] Tool call: list_notebooks[0m\n[36mℹ️  [11:30:22] 🔧 [TOOL] list_notebooks called[0m\n[32m✅  [11:30:22] ✅ [TOOL] list_notebooks completed (0 notebooks)[0m\n[36mℹ️  [11:30:22] 🔧 [MCP] Tool call: get_library_stats[0m\n[36mℹ️  [11:30:22] 🔧 [TOOL] get_library_stats called[0m\n[32m✅  [11:30:22] ✅ [TOOL] get_library_stats completed[0m\n[36mℹ️  [11:30:22] 🔧 [MCP] Tool call: list_sessions[0m\n[36mℹ️  [11:30:22] 🔧 [TOOL] list_sessions called[0m\n[32m✅  [11:30:22] ✅ [TOOL] list_sessions completed (0 sessions)[0m\n[36mℹ️  [11:30:22] 🔧 [MCP] Tool call: get_health[0m\n[36mℹ️  [11:30:22] 🔧 [TOOL] get_health called[0m\n[32m✅  [11:30:22] ✅ [TOOL] get_health completed[0m\n[36mℹ️  [11:30:22] 🔧 [MCP] Tool call: get_audio_status[0m\n[36mℹ️  [11:30:22] 🔧 [TOOL] get_audio_status called[0m\n[31m❌  [11:30:22] ❌ [TOOL] get_audio_status failed: Notebook URL is required to create a session[0m\n"},"tools":[{"name":"ask_question","description":"# Conversational Research Partner (NotebookLM • Gemini 2.5 • Session RAG)\n\n## No Active Notebook\n- Visit https://notebooklm.google to create a notebook and get a share link\n- Use **add_notebook** to add it to your library (explains how to get the link)\n- Use **list_notebooks** to show available sources\n- Use **select_notebook** to set one active\n\n> Auth tip: If login is required, use the prompt 'notebooklm.auth-setup' and then verify with the 'get_health' tool. If authentication later fails (e.g., expired cookies), use the prompt 'notebooklm.auth-repair'.\n\nTip: Tell the user you can manage NotebookLM library and ask which notebook to use for the current task.","params":["question","session_id","notebook_id","notebook_url","source_format","show_browser","browser_options"]},{"name":"add_notebook","description":"Register a NotebookLM notebook in the local library so it can be queried with `ask_question`, ingested into with `add_source`, etc.\n\n## Required URL\nThe user must supply a NotebookLM share-link. To produce one:\n  1. Open https://notebooklm.google\n  2. Open the notebook → click \"Share\" (top right)\n  3. Set \"Anyone with the link\" → \"Copy link\"\n\n## Permission workflow\nDo NOT call this tool unprompted. The expected dialogue is:\n  1. Ask for the URL\n  2. Ask what knowledge it contains (1–2 sentences) → `description`\n  3. Ask which topics it covers (3–5) → `topics`\n  4. Ask when it should be consulted → `use_cases`\n  5. Propose a `name` and the metadata back to the user\n  6. Only after explicit confirmation, call `add_notebook`.\n\nFree-tier limits: 100 notebooks · 50 sources each · 50 queries/day. Google AI Pro/Ultra raises these 5×.","params":["url","name","description","topics","content_types","use_cases","tags"]},{"name":"list_notebooks","description":"List every notebook in the local library with its metadata (`id`, `name`, `description`, `topics`, `tags`, `url`, `use_count`, etc.). Use the returned `id` for `select_notebook`, `update_notebook`, `get_notebook`, `remove_notebook`, or as `notebook_id` on `ask_question` / `add_source` / audio tools.","params":[]},{"name":"get_notebook","description":"Fetch full metadata for one notebook by id. Use to verify what's currently stored before calling `update_notebook`, or to show the user the exact `description`/`topics`/`use_cases` Claude has for it.","params":["id"]},{"name":"select_notebook","description":"Mark a notebook as the active default. After this, `ask_question`, `add_source`, and the audio tools resolve to that notebook when the caller omits `notebook_id` / `notebook_url`.\n\nWhen to call:\n  • The user explicitly switches context (e.g. \"Let's work on React now\")\n  • Task obviously needs a different notebook than the current one — announce the switch (\"Switching to the React notebook…\") before calling.\n  • If the right notebook is ambiguous, ask the user first instead of guessing.","params":["id"]},{"name":"update_notebook","description":"Patch metadata fields on an existing notebook. Pass `id` plus any subset of `name`, `description`, `topics`, `content_types`, `use_cases`, `tags`, `url` — only supplied fields change.\n\nWorkflow: identify the target notebook → propose the exact change back to the user → call only after explicit confirmation. Multiple fields can be updated in one call.","params":["id","name","description","topics","content_types","use_cases","tags","url"]},{"name":"remove_notebook","description":"Remove a notebook from the local library. **Does NOT delete the actual NotebookLM notebook on Google's side** — only the local metadata entry. Active sessions on this notebook are closed.\n\nConfirmation workflow: look up the notebook by id, ask the user \"Remove '[name]' from your library?\" — only call after a clear yes.","params":["id"]},{"name":"search_notebooks","description":"Search the library by free-text query — matches against `name`, `description`, `topics`, and `tags`. Returns notebook objects with their `id` so you can chain into `select_notebook` etc.\n\nUse this when the user references a notebook by topic (\"the React one\") instead of by exact name. If multiple notebooks match, propose the top 1–2 and let the user choose.","params":["query"]},{"name":"get_library_stats","description":"Aggregate statistics about the local notebook library: `total_notebooks`, `active_notebook` (id), `most_used_notebook`, `total_queries`, `last_modified`. Useful as a quick health check or when the user asks \"what notebooks do I have?\".","params":[]},{"name":"list_sessions","description":"List all active browser sessions for this server. Each entry includes `id`, `created_at`, `last_activity`, `age_seconds`, `inactive_seconds`, `message_count`, and `notebook_url`. Useful before `reset_session` / `close_session` or to recover a `session_id` you can pass back into `ask_question` to continue an existing conversation. Sessions older than `session_timeout` (see `get_health`) are auto-closed.","params":[]},{"name":"close_session","description":"Permanently close a session and discard its browser tab. Use the `id` returned by `list_sessions` (or the `session_id` from a prior `ask_question` response). Closed sessions cannot be resumed — start a new one with `ask_question` (no `session_id`) or pick another from `list_sessions`. Ask the user before closing if the session might still be needed.","params":["session_id"]},{"name":"reset_session","description":"Clear a session's chat history while keeping the same session id. Use this when the task changes mid-conversation and you want a fresh context without losing the underlying browser tab. Ask the user before resetting if they might still need the prior history.","params":["session_id"]},{"name":"get_health","description":"Inspect server state. Returns:\n  • `authenticated` — whether saved Google cookies are still valid\n  • `notebook_url`, `active_notebook_id`, `active_notebook_name` —\n    the currently selected library notebook (or null)\n  • `total_notebooks` — library size\n  • `active_sessions`, `max_sessions`, `session_timeout` — runtime\n    session stats (timeout in seconds; sessions auto-close after this)\n  • `headless`, `auto_login_enabled`, `stealth_enabled` — config\nUse this first thing in a new conversation. If `authenticated=false`, run `setup_auth` (or `re_auth` to switch accounts).","params":[]},{"name":"setup_auth","description":"Open a browser window for first-time Google login. Returns immediately after spawning the browser; the user has up to 10 minutes to complete sign-in, then cookies are persisted for future runs.\n\nWhen to use:\n  • `get_health` reports `authenticated=false` for the first time\n  • Auto-login credentials are not configured\n  • `re_auth` is the right call when you want to *switch* accounts or recover from a daily-quota lockout\n\nAfter login finishes, call `get_health` to verify success.\n\nIf the browser session feels broken (auth keeps failing, stale cookies), run `cleanup_data(confirm=true, preserve_library=true)` first, then retry `setup_auth`.","params":["show_browser","browser_options"]},{"name":"re_auth","description":"Switch to a different Google account or recover from broken auth. Closes all active sessions, deletes saved cookies and Chrome profile, and opens a fresh login browser.\n\nCommon triggers:\n  • NotebookLM's 50 queries/day free-tier limit is reached and the user wants to rotate to another Google account\n  • `setup_auth` failed and a clean slate is needed\n\nAfter login, call `get_health` to verify. For very stuck states, run `cleanup_data(confirm=true, preserve_library=true)` before `re_auth`.","params":["show_browser","browser_options"]},{"name":"cleanup_data","description":"Two-phase deep cleanup of all server data on disk (auth state, browser profiles, caches, MCP logs, temp backups). Cross-platform (Linux/macOS/Windows). Always close all Chrome/Chromium instances first — open browsers can lock files.\n\nPhase 1 (preview): call with `confirm: false`. Returns a categorised list of paths and total size. **No deletion happens.**\nPhase 2 (delete): after the user reviews the preview and approves, call with `confirm: true`.\n\nSet `preserve_library: true` to keep the notebook library file (library.json) while wiping everything else — recommended when troubleshooting auth.\n\nTypical recovery flow:\n  1. cleanup_data(confirm=false, preserve_library=true)  // preview\n  2. cleanup_data(confirm=true, preserve_library=true)   // execute\n  3. setup_auth (or re_auth)","params":["confirm","preserve_library"]},{"name":"add_source","description":"Ingest a source into a NotebookLM notebook. Supports two source types in v2.0:\n  • `url` — NotebookLM crawls and indexes a website\n  • `text` — paste raw text (treated as a copied document)\n\nFile / YouTube / Google-Drive uploads are not yet implemented.\n\nReturns `sourceCountBefore`/`sourceCountAfter` so the caller can verify the new source landed. Call once per source — multiple sources require multiple calls. NotebookLM finishes indexing within 5–30 seconds; subsequent `ask_question` calls then have the new source in context. Free notebooks cap at 50 sources.\n\nKnown quirk: pasted-text uploads occasionally redirect to a freshly created \"Untitled notebook\" on Google's side. The tool detects this and returns a clear error so you can re-try against the correct URL.","params":["type","content","title","show_browser","session_id","notebook_id","notebook_url"]},{"name":"generate_audio","description":"Trigger podcast-style Audio Overview generation for a notebook.\n\n**Async by default** — returns immediately with one of:\n  • `status: \"started\"` — generation just kicked off\n  • `status: \"in_progress\"` — a generation was already running; this call attached to it\n  • `status: \"ready\"` (with `alreadyExisted: true`) — an Audio Overview already existed; nothing was triggered\n\nGeneration typically takes 2–10 minutes. **Workflow:**\n  1. `generate_audio` → returns immediately\n  2. Poll `get_audio_status` every ~30 s\n  3. When status is `ready`, call `download_audio`\n\nPass `wait_for_completion: true` for legacy synchronous behaviour (blocks for up to `timeout_ms`). Audio Overview is the only Studio output exposed in v2.0 (Video / Mindmap / Quiz / Infographic / Datatable / Presentation are NotebookLM features but not yet wrapped).","params":["custom_prompt","wait_for_completion","timeout_ms","show_browser","session_id","notebook_id","notebook_url"]},{"name":"get_audio_status","description":"Non-blocking probe for the current Audio Overview state of a notebook.\n\nReturned `status` values:\n  • `ready` — Audio Overview is generated and ready to download\n  • `in_progress` — generation is currently running\n  • `not_started` — no Audio Overview exists yet for this notebook\n\nSafe to poll every ~30 s while waiting for `generate_audio` to finish. When status flips to `ready`, call `download_audio` with a destination directory.","params":["show_browser","session_id","notebook_id","notebook_url"]},{"name":"download_audio","description":"Save the completed Audio Overview to disk as a `.m4a` file. **Pre-condition:** `get_audio_status` must report `status: \"ready\"`. Calling this before generation completes returns an error message explaining what to do.\n\nThe file lands in `destination_dir` with NotebookLM's suggested filename (sanitised — usually the audio's title with underscores). The full saved path is returned in `result.filePath`.","params":["destination_dir","show_browser","session_id","notebook_id","notebook_url"]}],"toolsHash":"cb93dc94d466b86be5ca73560ba5f3cfa937fe74c04b1fd26ff87c64acf8381c","wrote":["/tmp/.local/share/notebooklm-mcp/library.json"],"callsAt":"2026-11-16T11:30:21.957Z","calls":[{"tool":"list_notebooks","ok":true,"ms":3,"bytes":58},{"tool":"get_library_stats","ok":true,"ms":1,"bytes":197},{"tool":"list_sessions","ok":true,"ms":1,"bytes":193},{"tool":"get_health","ok":true,"ms":1,"bytes":568},{"tool":"get_audio_status","ok":true,"ms":1,"bytes":81}],"host":{"commit":"eaaffffaf52255d1b77dc4aacffdfaf353f0c12c","run":"https://github.com/itsHaddad/bragproof/actions/runs/43857070216"},"network":{"names":["registry.npmjs.org"],"conns":[],"callNames":[],"callConns":[]}},"summary":{"outcome":"started","needs":[],"contacts":[],"flags":[],"tools":20,"wrote":1,"callsTried":5,"callsAnswered":5,"callContacts":[]},"history":[{"package":"notebooklm-mcp","version":"2.0.0","ranAt":"2026-11-16T11:30:14.829Z","outcome":"started","tools":20,"contacts":0,"flags":0,"serious":0,"toolsHash":"cb93dc94d466b86be5ca73560ba5f3cfa937fe74c04b1fd26ff87c64acf8381c"}],"page":"https://bragproof.smaverk.com/r/notebooklm-mcp"}