Manage Workflowy Lists with AI

Workflowy MCP is a Model Context Protocol server that connects AI assistants to Workflowy, letting them read and manipulate your Workflowy lists programmatically. It authenticates with your Workflowy username and password, then exposes tools to list, search, create, update, and complete nodes - the outline items Workflowy organizes everything into.

Use this when you keep project notes, milestones, or tasks in Workflowy and want an assistant to read and act on them directly - checking notes on a project, marking completed items done after reviewing a codebase, or suggesting next steps based on your milestones. It's well suited to using Workflowy as a project-management layer alongside AI-assisted work. It is not useful without a Workflowy account, and since it authenticates with your actual username and password, credentials should be stored as environment variables or in a .env file rather than hardcoded.

Example prompts the author reports using day to day: "Show my all my notes on project XYZ in workflowy", "Review the codebase, mark all completed notes as completed", and "Given my milestones on workflowy for this project, suggest what my next task should be."

• list_nodes: gets a list of nodes from Workflowy - root nodes, or children of a specified node.
• search_nodes: searches for nodes by query text.
• create_node: creates a new node in Workflowy.
• update_node: modifies an existing node's text or description.
• toggle_complete: marks a node as complete or incomplete.

Install globally or run directly with npx:

# Install the package globally
npm install -g mcp-workflowy

# Or use npx to run it directly
npx mcp-workflowy server start

Create a .env file with your credentials:

WORKFLOWY_USERNAME=your_username_here
WORKFLOWY_PASSWORD=your_password_here

Start the server with mcp-workflowy server start (or via npx), then connect your AI assistant to it per the assistant's MCP configuration. A one-click VS Code install is also available. Requires Node.js v18+ and shows live NPM version and download-count badges in the repository so you can check package activity before installing.

Integrating it with an AI assistant is a three-step process: start the MCP server as described above, connect the assistant to it per that assistant's own MCP documentation, and the assistant can then read and manipulate the Workflowy lists directly.

Anyone using Workflowy as their project management or notes tool who wants an AI assistant to read, search, and update their outline directly - reviewing project notes, marking items complete, or suggesting next tasks based on existing milestones.