Webflow MCP Server
This MCP server enables Claude to interact with Webflow's APIs.
Prerequisites
- Node.js (v16 or higher)
- Claude Desktop App
- Webflow Account
- Webflow API Token (Site token or OAuth Acces Token)
Setup Instructions
1. Create a Webflow API Token
- Log in to your Webflow account
- Navigate to Site Settings > Apps & Integrations
- Generate a new API token
- Copy the token value (you won't be able to see it again)
Alternatively, you can also generate an OAuth Access Token.
2. Initial Project Setup
Install dependencies:
npm install
3. Configure Environment Variables
Create a .env file for local development (don't commit this file):
WEBFLOW_API_TOKEN=your-api-token
4. Configure Claude Desktop
Open your Claude Desktop configuration file:
For MacOS:
code ~/Library/Application\\ Support/Claude/claude_desktop_config.json
For Windows:
code %AppData%\\Claude\\claude_desktop_config.json
Add or update the configuration:
{
"mcpServers": {
"webflow": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/YOUR/build/index.js"
],
"env": {
"WEBFLOW_API_TOKEN": "your-api-token"
}
}
}
}
Save the file and restart Claude Desktop.
Installing via Smithery
To install Webflow MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @kapilduraphe/webflow-mcp-server --client claude
Available Tools
The server currently provides the following tools:
get_sites
Retrieves a list of all Webflow sites accessible to the authenticated user. Returns detailed information including:
- Site Display Name and Short Name
- Site ID and Workspace ID
- Creation, Last Updated, and Last Published Dates
- Preview URL
- Time Zone settings
- Custom Domains configuration
- Localization settings (primary and secondary locales)
- Data collection preferences
get_site
Retrieves detailed information about a specific Webflow site by ID. Requires a siteId parameter and returns the same detailed information as get_sites for a single site.
Type Definitions
interface WebflowApiError {
status?: number;
message: string;
code?: string;
}
interface WebflowCustomDomain {
id: string;
url: string;
lastPublished: string;
}
interface WebflowLocale {
id: string;
cmsLocaleId: string;
enabled: boolean;
displayName: string;
redirect: boolean;
subdirectory: string;
tag: string;
}
interface WebflowSite {
id: string;
workspaceId: string;
createdOn: string;
displayName: string;
shortName: string;
lastPublished: string;
lastUpdated: string;
previewUrl: string;
timeZone: string;
parentFolderId?: string;
customDomains: WebflowCustomDomain[];
locales: {
primary: WebflowLocale;
secondary: WebflowLocale[];
};
dataCollectionEnabled: boolean;
dataCollectionType: string;
}
Error Handling
The server handles various error scenarios:
Environment Errors
- Missing WEBFLOW_API_TOKEN
- Invalid API token
Troubleshooting
Common Issues
Tools not appearing in Claude
- Check Claude Desktop logs
- Verify WEBFLOW_API_TOKEN is set correctly
- Ensure the path to index.js is absolute and correct
Authentication Errors
- Verify your API token is valid
- Check if the token has the necessary permissions
- Ensure the token hasn't expired
Viewing Logs
To view server logs:
For MacOS/Linux:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
For Windows:
Get-Content -Path "$env:AppData\\Claude\\Logs\\mcp*.log" -Wait -Tail 20
Environment Variables
If you're getting environment variable errors, verify:
WEBFLOW_API_TOKEN: Should be a valid API token
Security Considerations
- Keep your API token secure
- Don't commit credentials to version control
- Use environment variables for sensitive data
- Regularly rotate API tokens
- Monitor API usage in Webflow
- Use minimum required permissions for API token
Support
If you encounter any issues:
- Check the troubleshooting section above
- Review Claude Desktop logs
- Examine the server's error output
- Check Webflow's API documentation
License
MIT License - See LICENSE file for details.
Recommend MCP Servers 💡
telnyx-mcp-server
Official Telnyx MCP Server enabling interaction with telephony, messaging, and AI assistant APIs for MCP clients.
@confluentinc/mcp-confluent
An MCP server implementation that enables AI assistants to interact with Confluent Cloud REST APIs. This server allows AI tools like Claude Desktop and Goose CLI to manage Kafka topics, connectors, and Flink SQL statements through natural language interactions.
Defang MCP Server
Defang is an AI-enabled cloud deployment platform that simplifies deploying applications to various cloud providers (AWS, GCP, DigitalOcean) with a single command, handling infrastructure complexities like security, scalability, and cost-efficiency.
mcp-k8s
A Kubernetes MCP (Model Control Protocol) server that enables interaction with Kubernetes clusters through MCP tools.
metoro-mcp-server
Metoro MCP Server allows you to interact with your Kubernetes cluster via the Claude Desktop App!
mailjet
Enables AI agents to interact with Mailjet's email marketing APIs (contacts, campaigns, statistics, etc.) through a standardized Model Context Protocol interface.