Webflow MCP is a Node.js server that implements the Model Context Protocol (MCP) to enable AI agents to interact with Webflow APIs using the Webflow JavaScript SDK. It provides a bridge between AI tools and Webflow's data management capabilities.
Before getting started, ensure you have:
Add the following configuration to your AI editor:
{
"mcpServers": {
"webflow": {
"command": "npx",
"args": ["-y", "[email protected]"],
"env": {
"WEBFLOW_TOKEN": "<YOUR_WEBFLOW_TOKEN>"
}
}
}
}
+ Add New Global MCP Server
<YOUR_WEBFLOW_TOKEN>
with your actual tokenEdit Config
claude_desktop_config.json
in a code editor<YOUR_WEBFLOW_TOKEN>
with your actual tokenConfirm Node.js and NPM are properly installed:
node -v
npm -v
If you encounter issues with npx
, try clearing your NPM cache:
npm cache clean --force
If npm -v
works only with sudo, you may need to fix permissions following the NPM documentation.
sites - list; // List all sites
sites - get; // Get site details
sites - publish; // Publish site changes
pages - list; // List all pages
pages - get - metadata; // Get page metadata
pages - update - page - settings; // Update page settings
pages - get - content; // Get page content
pages - update - static - content; // Update page content
collections - list; // List collections
collections - get; // Get collection details
collections - create; // Create a collection
collection - fields - create - static; // Create a static field
collection - fields - create - option; // Create an option field
collection - fields - create - reference; // Create a reference field
collection - fields - update; // Update a custom field
collections - items - create - item - live; // Create items
collections - items - update - items - live; // Update items
collections - items - list - items; // List collection items
collections - items - create - item; // Create collection items (staged)
collections - items - update - items; // Update collection items (staged)
collections - items - publish - items; // Publish collection items
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.