NotebookLM Content Pipeline
NotebookLM does the research, Claude writes the content. Research → Synthesis → Content Creation → Publishing. Claude Code Skill + MCP Server.
What is NotebookLM Content Pipeline?
NotebookLM Content Pipeline is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to notebooklm does the research, claude writes the content. research → synthesis → content creation → publishing. claude code skill + mcp server.
NotebookLM does the research, Claude writes the content. Research → Synthesis → Content Creation → Publishing. Claude Code Skill + MCP Server.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- NotebookLM does the research, Claude writes the content. Res
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx notebooklm-skillConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use NotebookLM Content Pipeline
NotebookLM Skill is a Claude Code skill and MCP server that automates a full research-to-content pipeline by orchestrating Google's NotebookLM for deep source analysis and Claude for writing and publishing. You feed it URLs, PDFs, or YouTube links; NotebookLM creates a notebook, synthesizes citations and key findings, and Claude then drafts articles, reports, or podcast transcripts from those findings. It exposes 13 MCP tools covering notebook lifecycle management, source addition, research querying, summarization, and nine artifact types including audio summaries, slides, quizzes, and mind maps — all without requiring any API keys beyond a Google account login.
Prerequisites
- Python 3.10+ and uv or pip installed
- A Google account with access to NotebookLM (notebooklm.google.com)
- A browser session for initial Google login authentication
- Claude Code CLI or an MCP-compatible client such as Claude Desktop
Install notebooklm-skill
Install from PyPI using pip, or use uvx for zero-install execution. The uvx method is recommended as it requires no environment management.
# Recommended (zero install):
uvx notebooklm-skill --help
# Or via pip:
pip install notebooklm-skill
# Or from source:
git clone https://github.com/claude-world/notebooklm-skill.git
cd notebooklm-skill && pip install .Authenticate with your Google account
Run the login command to open a browser window and complete Google authentication. Credentials are saved to ~/.notebooklm/storage_state.json and persist for weeks.
# With uvx:
uvx notebooklm login
# With pip install:
python3 -m notebooklm loginTest the CLI to confirm authentication works
List existing notebooks to verify the login was successful before connecting to an MCP client.
uvx notebooklm-skill listConfigure the MCP server in your client
Add the notebooklm MCP server to your .mcp.json or claude_desktop_config.json file. The server is launched on demand via uvx.
{
"mcpServers": {
"notebooklm": {
"command": "uvx",
"args": ["--from", "notebooklm-skill", "notebooklm-mcp"]
}
}
}Install the Claude Code skill (optional)
If using Claude Code, place the SKILL.md file in your project's skills directory to give Claude the research-to-content pipeline workflow.
mkdir -p .claude/skills/notebooklm
cp /path/to/notebooklm-skill/SKILL.md .claude/skills/notebooklm/NotebookLM Content Pipeline Examples
Client configuration
MCP server configuration for Claude Desktop or .mcp.json using uvx to launch the notebooklm-mcp server.
{
"mcpServers": {
"notebooklm": {
"command": "uvx",
"args": ["--from", "notebooklm-skill", "notebooklm-mcp"]
}
}
}Prompts to try
Example prompts for running research-to-content pipelines and generating artifacts via NotebookLM.
- "Create a NotebookLM notebook from these three URLs and give me a summary of key findings."
- "Add this PDF as a source to my existing notebook and ask: what are the main arguments?"
- "Generate an audio summary podcast from the AI Research notebook."
- "Run the research-to-article pipeline on this YouTube video and publish a blog post draft."
- "Create flashcards from the notebook about machine learning fundamentals."Troubleshooting NotebookLM Content Pipeline
Login fails or browser does not open during authentication
Run uvx notebooklm login in a terminal with a graphical display available (not over SSH without X forwarding). The login command uses a headless browser internally — ensure Chrome or Chromium is installed on your system.
MCP tools return authentication errors after working previously
Google session credentials expire after several weeks. Re-run uvx notebooklm login to refresh the session. The new credentials overwrite ~/.notebooklm/storage_state.json automatically.
Artifact generation (podcast, slides) returns timeout errors
NotebookLM artifact generation is asynchronous and can take several minutes for large notebooks. Wait and retry, or reduce the number of sources in the notebook before requesting artifact generation.
Frequently Asked Questions about NotebookLM Content Pipeline
What is NotebookLM Content Pipeline?
NotebookLM Content Pipeline is a Model Context Protocol (MCP) server that notebooklm does the research, claude writes the content. research → synthesis → content creation → publishing. claude code skill + mcp server. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install NotebookLM Content Pipeline?
Follow the installation instructions on the NotebookLM Content Pipeline GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with NotebookLM Content Pipeline?
NotebookLM Content Pipeline works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is NotebookLM Content Pipeline free to use?
Yes, NotebookLM Content Pipeline is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
NotebookLM Content Pipeline Alternatives — Similar Coding Agents Servers
Looking for alternatives to NotebookLM Content Pipeline? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up NotebookLM Content Pipeline in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use NotebookLM Content Pipeline?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.