Webflow MCP server
The Model Context Protocol (MCP) server connects your AI tools directly to your Webflow projects. Prompt an AI agent to update designs, manage site data, and work with the CMS from your preferred AI environment.
For developers using AI-powered tools like Claude Code, Claude Desktop, Cursor, or Windsurf, the MCP server enhances an agent’s understanding of your Webflow projects. It’s built on Webflow’s APIs, exposing them as tools your AI agent can use to create elements, styles, and variables on the canvas, as well as manage collections, custom code, assets, and other site data.
Why use the MCP server?
Skip writing API calls and managing authentication. Just describe what you want in natural language, and your AI agent handles the implementation using Webflow’s Data and Designer APIs.
What you can do
Build and design
Manage content
Automate workflows
Get information
Use Designer API tools to create and modify visual elements on the canvas:
- Create layouts: Build responsive sections, containers, and grids with proper breakpoint configurations
- Style elements: Apply classes, modify CSS properties, and manage design variables
- Build components: Create reusable component definitions
- Design systems: Set up color schemes, typography scales, and spacing systems
Limitations
The MCP server can not automate all Webflow developer tools. Here are some of its major limitations:
- The MCP server does not yet have access to all endpoints in the Data and Designer APIs.
- The MCP server cannot control access to sites and Workspaces.
- To make changes to a site design, the MCP server requires the MCP Bridge App to be open.
- The MCP server does not support creating new localized CMS items, though it can read and update existing CMS items and static content in secondary locales.
Get started
Browse ready-to-use prompts for image optimization, SEO audits, style refactoring, and more.
Install skills that help you accomplish common Webflow tasks through natural language.
See information about what you can do through your AI agent, including using the Data API and Designer API.
Understand the architecture, authentication, and how the MCP server connects to Webflow’s APIs.
