Home / MCP / Webflow MCP Server

Webflow MCP Server

Enables AI agents to read and modify Webflow data via MCP for automated site workflows.

javascript

90stars

View on GitHub

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
    "mcpServers": {
        "webflow": {
            "url": "https://mcp.webflow.com/sse"
        }
    }
}

This MCP server lets you connect Webflow to AI agents through the Model Context Protocol, enabling seamless querying, editing, and automation of Webflow sites from your AI client. It supports remote MCP usage and local setups, so you can choose the workflow that fits your needs.

How to use

You enable the MCP server and connect it to your AI client or design environment. The remote setup lets you authenticate with Webflow sites via OAuth and then interact with the Webflow Data API through your AI agent. You can access the Webflow Designer, launch the Webflow MCP Bridge App from the Apps panel, and issue prompts to analyze content, add internal links, or create page components.

Common usage patterns include analyzing your latest posts to generate SEO-friendly topic ideas, finding older posts to link internally, and constructing UI components like hero sections with responsive designs. You can try prompts such as: Analyze my last 5 blog posts and suggest 3 new topic ideas with SEO keywords and Create a hero section card on my home page with a CTA button and responsive design.

How to install

Prerequisites you need before installing are Node.js, NPM, and a Webflow account.

Remote installation steps assume you want to run the MCP server remotely and authenticate with Webflow sites. Ensure Node.js is version 22.3.0 or higher.

{
  "mcpServers": {
    "webflow": {
      "url": "https://mcp.webflow.com/sse"
    }
  }
}

Reset your OAuth token

If you need to reset your OAuth token, run the following command in your terminal.

rm -rf ~/.mcp-auth

Node.js compatibility

Please ensure you are using a supported Node.js version. Check the latest compatibility guidance for Webflow and MCP server tooling to avoid version-related issues.

Troubleshooting

If you encounter issues starting the server in your MCP client, verify you have a valid Webflow API token, and restart your MCP client after saving any configuration changes.

Verify Node.js and NPM are installed by checking their versions.

node -v
npm -v

Optional: Run locally via shell

You can run the local MCP server from the shell using your Webflow API token.

WEBFLOW_TOKEN="<YOUR_WEBFLOW_TOKEN>" npx -y webflow-mcp-server@latest

Open the Webflow Designer and App

In the Webflow Designer, you can access the Apps panel and launch the published Webflow MCP Bridge App. This connects the Designer to the MCP server so you can issue prompts from your AI client and observe results directly in Webflow.