Canvas Notebook
Canvas Notebook — Your AI workspace with file management, agent support, and bring-your-own-model flexibility.
What is Canvas Notebook?
Canvas Notebook is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to canvas notebook — your ai workspace with file management, agent support, and bring-your-own-model flexibility.
Canvas Notebook — Your AI workspace with file management, agent support, and bring-your-own-model flexibility.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Canvas Notebook — Your AI workspace with file management, ag
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx canvas-notebookConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Canvas Notebook
Canvas Notebook is a self-hosted AI workspace that combines a file browser, code editor, terminal, chat interface, to-do manager, email client, and media generation studio in a single application. It supports multiple AI providers including Anthropic Claude, OpenAI, Google Gemini, Ollama, Groq, and Mistral, and exposes an MCP server so external agents can interact with the workspace programmatically.
Prerequisites
- Docker and Docker Compose installed (for Linux/VPS deployment)
- Node.js 18+ and npm (for local macOS/Windows installation)
- A domain name with DNS configured (for HTTPS on Linux servers)
- At least one AI provider API key (Anthropic, OpenAI, Gemini, Groq, Mistral, or a local Ollama instance)
- 2 GB RAM minimum; 4 GB recommended for running local models via Ollama
Install Canvas Notebook
On Linux or a VPS, use the automated installer which sets up Docker containers, generates secrets, and optionally configures HTTPS via Let's Encrypt. On macOS or Windows, clone the repository and run npm setup.
# Linux/VPS (recommended)
bash <(curl -fsSL https://raw.githubusercontent.com/canvascoding/canvas-notebook/main/install.sh)
# macOS/Windows from source
git clone https://github.com/canvascoding/canvas-notebook.git
cd canvas-notebook
npm run setupConfigure environment variables
The installer auto-generates the required secrets, but you can set them manually if needed. BETTER_AUTH_SECRET must be a 32-byte base64 string. BETTER_AUTH_BASE_URL must match the public URL of your deployment.
# Required environment variables
BETTER_AUTH_SECRET=<32-byte-base64-string> # auto-generated by installer
CANVAS_INTERNAL_API_KEY=<random-secret> # auto-generated by installer
BETTER_AUTH_BASE_URL=https://canvas.example.com # your public URLAdd your AI provider API key
Open the Canvas Notebook settings UI after launch and enter your AI provider API key. Canvas Notebook supports OpenRouter, Anthropic, Google Gemini, Ollama, Groq, Mistral, and OpenAI. You can switch providers per conversation.
Install custom skills
Extend the workspace agent by dropping a folder containing a SKILL.md file into the /data/skills/ directory. Skills can include executable scripts in a bin/ subdirectory that the agent will discover and use automatically.
# skills directory structure
/data/skills/
my-skill/
SKILL.md # describes the skill to the agent
bin/
my-command.sh # executable the agent can callManage the Canvas Notebook service
After installation on Linux, use the canvas-notebook CLI to update, view logs, check status, or restart the service. These commands wrap the underlying Docker Compose operations.
canvas-notebook update # pull latest image and restart
canvas-notebook logs # stream service logs
canvas-notebook status # show running containers
canvas-notebook restart # restart all containers
canvas-notebook admin reset-password --email [email protected]Canvas Notebook Examples
Client configuration
Claude Desktop configuration to connect to a running Canvas Notebook MCP server endpoint.
{
"mcpServers": {
"canvas-notebook": {
"command": "npx",
"args": ["canvas-notebook"],
"env": {
"BETTER_AUTH_BASE_URL": "https://canvas.example.com",
"CANVAS_INTERNAL_API_KEY": "your-internal-api-key"
}
}
}
}Prompts to try
Example prompts to use within Canvas Notebook's built-in chat or via the MCP integration.
- "List the files in my workspace and summarise what each project does"
- "Create a new note titled 'Project Plan' with sections for Goals, Timeline, and Risks"
- "Run the test suite in /data/workspace/my-project and show me a summary of failures"Troubleshooting Canvas Notebook
The installer fails with 'docker: command not found' on a fresh Linux server
Install Docker before running the Canvas Notebook installer: curl -fsSL https://get.docker.com | sh && sudo systemctl enable --now docker. Then re-run the Canvas Notebook install script.
HTTPS certificate fails to issue during installation
Ensure your domain's A record points to the server's public IP and that ports 80 and 443 are open in your firewall. Let's Encrypt requires port 80 for the HTTP-01 challenge. Wait for DNS propagation before retrying.
AI provider returns authentication errors after entering the API key
Double-check the API key in the Canvas Notebook settings UI. Keys are stored in /data/secrets/ on the host. Ensure the key has the correct permissions for the selected model and that your account has sufficient credits.
Frequently Asked Questions about Canvas Notebook
What is Canvas Notebook?
Canvas Notebook is a Model Context Protocol (MCP) server that canvas notebook — your ai workspace with file management, agent support, and bring-your-own-model flexibility. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Canvas Notebook?
Follow the installation instructions on the Canvas Notebook GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Canvas Notebook?
Canvas Notebook works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Canvas Notebook free to use?
Yes, Canvas Notebook is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Canvas Notebook Alternatives — Similar Developer Tools Servers
Looking for alternatives to Canvas Notebook? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Canvas Notebook 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 Canvas Notebook?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.