NotebookLM MCP Server

- Node.js≥ 18.
- Chrome(stable channel) preferred. The bundled Patchright Chromium is used as a fallback when Chrome refuses to launch — setBROWSER_CHANNEL=chromiumto force it.
- Linux / macOS / Windows.
- WSL2 + WSLg(Windows 11+) is fully supported. WSL1 cannot launch a Chromium and is not supported — upgrade to WSL2.
- Headless Linux servers: the one-timesetup_authneeds a display because the login flow opens a visible window. Run it once underxvfb-run(xvfb-run -a npx notebooklm-mcp). After login, the persistent Chrome profile lets every subsequent run go fully headless.

This is the recommended path for end users.npxkeeps the binary cached and self-updates on@latest.

git clone https://github.com/PleasePrompto/notebooklm-mcp cd notebooklm-mcp npm install npm run build node dist/index.js

Thepreparescript also runsnpm run build, so a freshnpm installproduces a runnabledist/index.js.

claude mcp add notebooklm -- npx notebooklm-mcp@latest # or, from a local clone: claude mcp add notebooklm -- node /absolute/path/to/notebooklm-mcp/dist/index.js

Manual form — drop into~/.claude.json:

- setup_auth— first-time login. Passshow_browser=true(default for setup) to see the window. Returns immediately after launching the window; you have up to 10 min to complete the login.
- re_auth— wipe stored auth and start over. Use when switching Google accounts or when authentication is broken.
- cleanup_data— full cleanup with categorised preview. Passpreserve_library=trueto keeplibrary.jsonwhile wiping browser state.

To force a visible browser for any browser-driven tool, passshow_browser=trueorbrowser_options.show=trueon the tool call.

The server speaks MCP over either stdio or Streamable-HTTP.

npx notebooklm-mcp@latest --transport http --port 3000 # bind to all interfaces: npx notebooklm-mcp@latest --transport http --port 3000 --host 0.0.0.0

Equivalent env vars:NOTEBOOKLM_TRANSPORT=http,NOTEBOOKLM_PORT=3000,NOTEBOOKLM_HOST=0.0.0.0.

The server uses the MCP SDK'sStreamableHTTPServerTransport, which manages session lifecycle through theMcp-Session-Idresponse/request header. A new session is created when the firstPOST /mcpbody is aninitializerequest; from then on the client must echo the returnedMcp-Session-Idon every request.

Default host is127.0.0.1. Bind to0.0.0.0only when the server is reachable on a trusted network.

Run distinct Chrome profiles for different Google accounts:

npx notebooklm-mcp@latest --account work npx notebooklm-mcp@latest --account personal # or via env: NOTEBOOKLM_ACCOUNT=work npx notebooklm-mcp@latest

There is no encrypted credential store — isolation is purely by Chrome profile directory.

Resources (read-only):notebooklm://library,notebooklm://library/{id},notebooklm://metadata(deprecated, kept for backward compat).

Profiles trim the tool list to keep host-agent context budgets in check.

npx notebooklm-mcp config set profile minimal npx notebooklm-mcp config get

NOTEBOOKLM_PROFILE=standard npx notebooklm-mcp@latest

Disable specific tools regardless of profile:

npx notebooklm-mcp config set disabled-tools cleanup_data,re_auth # or NOTEBOOKLM_DISABLED_TOOLS=cleanup_data,re_auth npx notebooklm-mcp@latest

Settings are persisted in<configDir>/settings.json(XDG/%APPDATA%location, see config.ts).

ask_questionaccepts asource_formatargument that controls how the citation panel from the NotebookLM UI is folded into the response.

{ "name": "ask_question", "arguments": { "question": "How do I configure retry logic in n8n HTTP nodes?", "source_format": "footnotes" } }

Everyask_questionresult carries a_provenanceenvelope:

{ "_provenance": { "provider": "google-notebooklm", "model": "gemini-2.5", "via": "chrome-automation", "grounding": "user-uploaded-documents", "ai_generated": true } }

By default the answer text is also prefixed with an inline AI-generated marker:

npm run build # tsc + chmod +x dist/index.js npm run dev # tsx watch src/index.ts npm run lint # eslint src npm run format # prettier --write src npm run check # format:check + lint + build

The build is type-safe with noanycasts; DOM types are enabled for in-page evaluations.

- src/index.ts— CLI parsing, MCP wiring, transport selection
- src/transport/http.ts— Streamable-HTTP transport
- src/tools/definitions/— tool schemas
- src/tools/handlers.ts— tool implementations
- src/notebooklm/— selectors and DOM logic
- src/auth/— auth manager + account switcher
- src/library/— local notebook library
- src/utils/— settings, logger, disclaimer, cli-handler

v2 changes the following defaults — adjust if you depended on v1 behaviour:

- ANSWER_TIMEOUT_MSis600 000(was hard-coded120 000). Set explicitly to keep a 2-minute fail-fast.
- The follow-up reminder appended to answers is now off. Re-enable withNOTEBOOKLM_FOLLOW_UP_REMINDER=true.
- The AI-generated marker prefix is on by default. Disable withNOTEBOOKLM_AI_MARKER=false.

Give your AI assistant the ability to identify cognitive blind spots. The official Model Context Protocol (MCP) server for cognitivebiaslabs.com.

A cognitive framework selector to help choose the right mental models and thinking frameworks for any situation.

An MCP server for advanced cognitive analysis, creative problem-solving, and structured thinking using the UCPF framework.

An MCP server implementation that provides a tool for problem-solving using the Lotus Sutra's wisdom framework, combining analytical thinking with intuitive wisdom.

A private, local research "second brain" for Claude — cited answers from your own library (it won't invent what it can't find), persistent project memory, daily briefs, a live meeting assistant, and 34 specialist agents. Runs entirely on your machine.

Create notes, search, & think with your Fabric AI workspace

Great Question is an Agentic UX research platform for product builders. Its MCP lets AI agents create studies directly from any AI tool, surface insights, find the right research candidates, and query your entire research repository.

Prompt Buddy MCP exposes a public, searchable catalog of reusable AI skills.