MCP.so
Sign In

Webflow's Official MCP Server

@webflow

Basic information

Category

Other

License

MIT

Transports

stdio

Author

webflow

About Webflow's Official MCP Server

Model Context Protocol (MCP) server for the Webflow Data API.

#business-critical-yes#generated-from-openapi#built-with-fern#model-context-protocol#mcp-server

Webflow's Official MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-webflow": {
      "command": "npx",
      "args": [
        "-y",
        "webflow-mcp-server@latest"
      ],
      "env": {
        "WEBFLOW_TOKEN": "<YOUR_WEBFLOW_TOKEN>"
      }
    }
  }
}

Webflow's Official MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Webflow's Official MCP Server?

A Node.js server that implements the Model Context Protocol (MCP) using the Webflow JavaScript SDK, enabling AI agents to interact with Webflow’s APIs. It is designed for developers who want to build AI-powered tools for Webflow sites.

How to use Webflow's Official MCP Server?

Install remotely via OAuth (for Cursor or Claude Desktop) by adding an SSE URL configuration, or install locally by creating a Webflow MCP Bridge App, configuring an API token in your AI client, and running npx -y webflow-mcp-server@latest. After setup, open the Webflow Designer, launch the Webflow MCP Bridge App from the Apps panel, and start prompting your AI agent.

Key features of Webflow's Official MCP Server

  • Remote installation with OAuth authentication
  • Local installation using a Webflow API token
  • Compatible with Cursor and Claude Desktop
  • Integration with the Webflow Designer via a Bridge App
  • Requires Node.js 22.3.0 or higher
  • No built-in prompts or resources (planned for future)

Use cases of Webflow's Official MCP Server

  • Analyze blog posts and suggest topic ideas with SEO keywords
  • Find older posts mentioning similar topics and add internal links
  • Create hero section cards with CTA buttons and responsive design
  • Retrieve and update Webflow CMS content programmatically
  • Automate content management tasks through AI chat interfaces

Frequently asked questions

1

What are the prerequisites?

You need Node.js and NPM installed, a Webflow account, and either an OAuth token (remote installation) or a Webflow API token (local installation).

2

How does authentication work?

Remote installation uses OAuth (browser-based login); local installation requires a `WEBFLOW_TOKEN` environment variable set to a valid Webflow API token.

3

What is the known limitation of the server?

The `pages_update_static_content` endpoint currently supports only localized static pages in secondary locales—it does not support updates to the default locale.

4

Can I use it with local installation?

Yes. You must create and publish a Webflow MCP Bridge App in your workspace, then configure your AI client (Cursor or Claude Desktop) with a Webflow API token.

5

Does the server support prompts or resources?

Currently no. The implementation does not include MCP prompts or resources, but this may change when broader client support emerges.

Comments

More Other MCP servers