com.webflow/mcp MCP Server
com.webflow/mcp
AI-powered design and management for Webflow sites via the Webflow Data API.
What is the com.webflow/mcp MCP server?
The Webflow MCP server is a Node.js implementation of Model Context Protocol that enables AI agents to interact with Webflow APIs and manage Webflow sites. It integrates with the Webflow JavaScript SDK and Data API, allowing Claude and Cursor to read and modify site content, analyze blog posts, and create design elements directly in the Webflow Designer.
This MCP server connects AI agents to your Webflow sites, enabling tasks like analyzing blog content, suggesting SEO improvements, adding internal links, and creating responsive design sections. It works with both Cursor and Claude Desktop via OAuth authentication and includes a companion Webflow MCP Bridge App that syncs your live canvas with the AI agent.
How to install com.webflow/mcp
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
get_designer_app_connection_info— Retrieves connection information for the Webflow Designer Bridge App, used to establish local connections between the MCP server and the Designer.pages_update_static_content— Updates static page content in localized secondary locales (updates to default locale static content are not currently supported).
Use cases
- Analyze blog posts and generate SEO-optimized topic ideas with keywords
- Find related older blog posts and automatically add internal links to new content
- Create responsive hero sections with CTA buttons in the Webflow Designer
- Audit and improve site content structure and SEO metadata
- Manage site collections and content across multiple pages
com.webflow/mcp MCP server FAQ
It's a Node.js server that implements the Model Context Protocol for Webflow, allowing AI agents like Claude and Cursor to interact with your Webflow sites via the Webflow Data API. You can analyze content, modify pages, and create design elements directly from your AI chat.
Yes, the MCP server itself is free and open-source. You need a Webflow account and a valid Webflow API token to use it.
Go to Settings → Cursor Settings → MCP & Integrations, click '+ New MCP Server', and add the webflow configuration with URL 'https://mcp.webflow.com/sse'. Save and authorize via OAuth when prompted.
Enable Developer Mode, open claude_desktop_config.json, and add the webflow MCP server configuration with the command 'npx' and args ['mcp-remote', 'https://mcp.webflow.com/sse']. Restart Claude Desktop to complete OAuth authorization.
The remote server uses OAuth to authenticate with your Webflow sites. For local installation, you need a Webflow API token. You can reset your OAuth token by running 'rm -rf ~/.mcp-auth'.
Node.js 22.3.0 or higher and NPM are required. The server works with Cursor and Claude Desktop on macOS, Windows, and Linux.
README (reference)
Source of truth, from the repository.
Webflow's MCP server
A Node.js server implementing Model Context Protocol (MCP) for Webflow using the Webflow JavaScript SDK. Enable AI agents to interact with Webflow APIs. Learn more about Webflow's Data API in the developer documentation.
Prerequisites
🚀 Remote installation
Get started by installing Webflow's remote MCP server. The remote server uses OAuth to authenticate with your Webflow sites, and a companion app that syncs your live canvas with your AI agent.
Requirements
- Node.js 22.3.0 or higher
Note: The MCP server currently supports Node.js 22.3.0 or higher. If you run into version issues, see the Node.js compatibility guidance.
Cursor
Add MCP server to Cursor
- Go to
Settings → Cursor Settings → MCP & Integrations. - Under MCP Tools, click
+ New MCP Server. - Paste the following configuration into
.cursor/mcp.json(or add thewebflowpart to your existing configuration):
{
"mcpServers": {
"webflow": {
"url": "https://mcp.webflow.com/sse"
}
}
}
Tip: You can create a project-level
mcp.jsonto avoid repeated auth prompts across multiple Cursor windows. See Cursor’s docs on configuration locations.
- Save and close the file. Cursor will automatically open an OAuth login page where you can authorize Webflow sites to use with the MCP server.
Open the Webflow Designer
- Open your site in the Webflow Designer, or ask your AI agent:
Give me a link to open <MY_SITE_NAME> in the Webflow Designer
Open the MCP Webflow App
- In the Designer, open the Apps panel (press
E). - Launch your published "Webflow MCP Bridge App".
- Wait for the app to connect to the MCP server.
Write your first prompt
Try these in your AI chat:
Analyze my last 5 blog posts and suggest 3 new topic ideas with SEO keywords
Find older blog posts that mention similar topics and add internal links to my latest post
Create a hero section card on my home page with a CTA button and responsive design
Claude desktop
Add MCP server to Claude desktop
- Enable developer mode:
Help → Troubleshooting → Enable Developer Mode. - Open developer settings:
File → Settings → Developer. - Click
Get Startedor edit the configuration to openclaude_desktop_config.jsonand add:
{
"mcpServers": {
"webflow": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.webflow.com/sse"]
}
}
}
- Save and restart Claude Desktop (
Cmd/Ctrl + R). An OAuth login page will open to authorize sites.
Open the Webflow Designer
- Open your site in the Webflow Designer, or ask your AI agent:
Give me a link to open <MY_SITE_NAME> in the Webflow Designer
Open the MCP Webflow App
- In the Designer, open the Apps panel (press
E). - Launch your published "Webflow MCP Bridge App".
- Wait for the app to connect to the MCP server.
Write your first prompt
Analyze my last 5 blog posts and suggest 3 new topic ideas with SEO keywords
Find older blog posts that mention similar topics and add internal links to my latest post
Create a hero section card on my home page with a CTA button and responsive design
Reset your OAuth token
To reset your OAuth token, run the following command in your terminal.
rm -rf ~/.mcp-auth
Node.js compatibility
Please see the Node.js compatibility guidance on Webflow's developer docs.
Local Installation
You can also configure the MCP server to run locally. This requires:
- Creating and registering your own MCP Bridge App in a Webflow workspace with Admin permissions
- Configuring your AI client to start the local MCP server with a Webflow API token
1. Create and publish the MCP bridge app
Before connecting the local MCP server to your AI client, you must create and publish the Webflow MCP Bridge App in your workspace.
Steps
-
Register a Webflow App
- Go to your Webflow Workspace and register a new app.
- Follow the official guide: Register an App.
-
Get the MCP Bridge App code
- Option A: Download the latest
bundle.zipfrom the releases page. - Option B: Clone the repository and build it:
git clone https://github.com/virat21/webflow-mcp-bridge-app cd webflow-mcp-bridge-app- Then build the project following the repository instructions.
- Option A: Download the latest
-
Publish the Designer Extension
- Go to Webflow Dashboard → Workspace settings → Apps & Integrations → Develop → Your App.
- Click “Publish Extension Version”.
- Upload your built
bundle.zipfile.
-
Open the App in Designer
- Once published, open the MCP Bridge App from the Designer → Apps panel in a site within your workspace.
2. Configure your AI client
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"webflow": {
"command": "npx",
"args": ["-y", "webflow-mcp-server@latest"],
"env": {
"WEBFLOW_TOKEN": "<YOUR_WEBFLOW_TOKEN>"
}
}
}
}
Claude desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"webflow": {
"command": "npx",
"args": ["-y", "webflow-mcp-server@latest"],
"env": {
"WEBFLOW_TOKEN": "<YOUR_WEBFLOW_TOKEN>"
}
}
}
}
3. Use the MCP server with the Webflow Designer
- Open your site in the Webflow Designer.
- Open the Apps panel (press
E) and launch your published “Webflow MCP Bridge App”. - Wait for the app to connect to the MCP server, then use tools from your AI client.
- If the Bridge App prompts for a local connection URL, call the
get_designer_app_connection_infotool from your AI client and paste the returnedhttp://localhost:<port>URL.
Optional: Run locally via shell
WEBFLOW_TOKEN="<YOUR_WEBFLOW_TOKEN>" npx -y webflow-mcp-server@latest
# PowerShell
$env:WEBFLOW_TOKEN="<YOUR_WEBFLOW_TOKEN>"
npx -y webflow-mcp-server@latest
Reset your OAuth Token
To reset your OAuth token, run the following command in your terminal.
rm -rf ~/.mcp-auth
Node.js compatibility
Please see the Node.js compatibility guidance on Webflow's developer docs.
❓ Troubleshooting
If you are having issues starting the server in your MCP client e.g. Cursor or Claude Desktop, please try the following.
Make sure you have a valid Webflow API token
- Go to Webflow's API Playground, log in and generate a token, then copy the token from the Request Generator
- Replace
YOUR_WEBFLOW_TOKENin your MCP client configuration with the token you copied - Save and restart your MCP client
Make sure you have the Node and NPM installed
Run the following commands to confirm you have Node and NPM installed:
node -v
npm -v
Clear your NPM cache
Sometimes clearing your NPM cache can resolve issues with npx.
npm cache clean --force
Fix NPM global package permissions
If npm -v doesn't work for you but sudo npm -v does, you may need to fix NPM global package permissions. See the official NPM docs for more information.
Note: if you are making changes to your shell configuration, you may need to restart your shell for changes to take effect.
🛠️ Available tools
See the ./tools directory for a list of available tools
🗣️ Prompts & resources
This implementation doesn't include prompts or resources from the MCP specification. However, this may change in the future when there is broader support across popular MCP clients.
📄 Webflow developer resources
⚠️ Known limitations
Static page content updates
The pages_update_static_content endpoint currently only supports updates to localized static pages in secondary locales. Updates to static content in the default locale aren't supported and will result in errors.
Related MCP servers
WebforJ's MCP server, provides tools, resources, prompts for scaffolding and developing webforJ apps
Webhook Studio
Keyless webhook endpoints: capture, wait, replay, forward, and generate types from real traffic.
Send, retry and monitor webhooks: manage endpoints, event types and API keys (OAuth).
Build or create a webinar from chat: registration page, invitation emails, evergreen funnel.
Evaluate one public URL for WebMCP readiness: intent, tools observed, recommended, do-not-expose.
Scores any public website on how usable it is by AI agents, with per-check evidence.