MCP server and AI tools

Work with Webflow’s APIs using our official MCP server and AI tools

MCP Hero Image

Build faster with Webflow’s APIs using LLMs. Connect directly to your site data, access collection schemas, generate functional code, and solve development challenges with context from your Webflow projects.

Webflow’s official MCP server

For developers using AI-powered tools like Cursor or Claude Desktop, we provide a Model Context Protocol (MCP) server that enhances your AI agent’s understanding of your Webflow projects. The MCP server has tools that enable AI agents to access real-time information about your sites, collections, and other objects, enabling more accurate and contextual code suggestions and troubleshooting. To see a full list of tools, see the MCP server documentation.

Install Webflow’s official MCP server

Remote installation

Get started quickly by installing Webflow’s remote MCP server, which uses OAuth to authenticate with your Webflow sites. For local installation, see the local installation section below.

1

Go to Settings → Cursor Settings → MCP

2

Click + Add New Global MCP Server

3

Paste the following configuration into .cursor/mcp.json (or add the webflow part to your existing configuration)

.cursor/mcp.json
1{
2 "mcpServers": {
3 "webflow": {
4 "command": "npx mcp-remote https://mcp.webflow.com/sse"
5 }
6 }
7}
4

Save your file. Cursor will automatically open a new browser window showing an OAuth login page where you can authorize the Webflow sites you want the MCP server to access.

Webflow's remote MCP server is currently experimental

These installation methods rely on the mcp-remote npm package, which is currently considered experimental as of 05/01/2025.

Resetting your OAuth token

If you need to reset your OAuth token, you can run the following command before restarting your MCP client.

$rm -rf ~/.mcp-auth

Local installation

If you prefer to install the MCP server locally, you can do so by following the steps below. Local installation requires Node.js and npm to be installed on your machine.

Prerequisites

  • Node.js version 18 or higher
  • npm version 10 or higher

Steps

  1. Get a Webflow API token from the Webflow API Playground

    Webflow API token
  2. Add the following snippet to your client’s configuration file:

    1{
    2 "mcpServers": {
    3 "webflow": {
    4 "command": "npx",
    5 "args": ["-y", "webflow-mcp-server"],
    6 "env": {
    7 "WEBFLOW_TOKEN": "YOUR_API_TOKEN"
    8 }
    9 }
    10 }
    11}

    Remember to replace YOUR_API_TOKEN with your actual Webflow API token.

  3. Add the MCP server to your AI client:

    1Go to Settings → Cursor Settings → MCP
    2Click + Add New Global MCP Server
    3Paste configuration into .cursor/mcp.json
    Cursor MCP
    4Save and verify server status
    Cursor MCP
    5

    Start interacting with the MCP server

    In the “Chat” window, switch to “Agent Mode” and start interacting with the MCP server. You can ask the agent things like:

    • “When was my site last published?"
    • "What were the last 5 CMS items published to this site?"
    • "Based on my last 5 blog posts, can you generate some ideas for new blog posts?"
    • "What are the current SEO issues on my site and how can I fix them?”
    6

    Send us feedback!

    We’re just getting started with this, so we’d love to hear from you! If you’d like to see more tools or have any feedback, please log an issue on GitHub.


Documentation for LLMs

Webflow’s documentation is optimized for consumption by AI assistants, making it easier for these tools to generate accurate code examples and guidance.

  • Use https://developers.webflow.com/llms.txt to access the LLM-readable documentation. This optimized structure helps LLMs respond with accurate code snippets and multi-step sequences.
  • Additionally, you can access markdown versions of any documentation page to provide a more structured and context-rich experience for LLMs. To access the markdown version of a page, add .md to the end of the URL. For example, this current doc is available as a markdown file at https://developers.webflow.com/data/docs/ai-tools.md.

Installing docs on Cursor

1In the chat, click the @ button
2Find the “Docs” option
3Click “Add new doc”
4Paste in the following link: https://developers.webflow.com/llms.txt

Once configured, reference Webflow’s documentation by typing @Docs in your chat window and selecting “Webflow” from the list.


FAQs

After installing the MCP server, you may need to restart your AI client to see the new server. Additionally, check to see that your client (for example, Cursor, Claude Desktop) is updated to the latest version.

Ensure you have a valid Webflow API token

  1. Go to Webflow’s API Playground, log in and generate a token, then copy the token from the Request Generator
  2. Replace YOUR_WEBFLOW_TOKEN in your MCP client configuration with the token you copied
  3. Save and restart your MCP client

Ensure Node.js and NPM are properly installed

  1. Verify Node.js and NPM installation by running:
    $node -v
    >npm -v
  2. If you encounter issues with npx, try clearing your NPM cache:
    $npm cache clean --force
  3. If npm -v only works with sudo, you may need to fix NPM global package permissions. See the official NPM docs for more information.

If you make changes to your shell configuration, you may need to restart your shell for changes to take effect.

Built with