Overview
The Workflowy MCP server provides a Model Context Protocol (MCP) compatible interface to Workflowy, enabling AI assistants to read and manipulate your Workflowy lists programmatically. It authenticates with a Workflowy account using a username/password and exposes a set of MCP tools tailored for common list-management tasks. With this server, you can list root nodes or the children of a specified node, search nodes by text, create new nodes, update a node's text or description, and toggle a node's complete state. The server is designed to be used with AI assistants (such as ChatGPT), allowing natural language prompts to trigger MCP tool calls and modify Workflowy data in a structured, consistent manner. Prerequisites include Node.js v18+ and a Workflowy account. Installation can be done globally via npm install -g mcp-workflowy or by running npx mcp-workflowy server start. Configuration is via a .env file or environment variables (WORKFLOWY_USERNAME and WORKFLOWY_PASSWORD). The README demonstrates example prompts and provides a one-click VS Code install badge for quick setup. Contributing and licensing are noted in the repository.
Features
Workflowy Integration
Connect to your Workflowy account using username/password authentication.
MCP Compatibility
Full support for the Model Context Protocol.
Tool Operations
Search, create, update, and mark nodes as complete/incomplete in your Workflowy.
Who Is This For?
- AI assistants:Connect to the MCP server to read and manipulate your Workflowy lists programmatically.
- Developers/integrators:Install, configure, and run the MCP server to expose Workflowy interactions to AI assistants.




