We made multi-workspace MCP easy in Webflow. Now we’re sharing our tool.

The idea for MCP Router started with a practical frustration.

I wanted to work with multiple Webflow workspaces in ChatGPT and Codex, but I couldn’t get the connections to work reliably at the same time. In Claude Desktop, it was possible, but setting up and maintaining them was cumbersome.

Then there were the permissions. They were set for the connection as a whole, and changing them meant going through authorization again. But I didn’t necessarily want AI to have the same permissions on every project.

I wanted one place to manage my Webflow connections, choose which projects were available, and adjust what AI could do in each of them.

So I built MCP Router.

What MCP Router makes easier

MCP Router is a desktop app for macOS and Windows that connects your local AI tools to Webflow’s MCP server. You add your Webflow connections once, then make them available through a single MCP connection in each AI tool.

Here’s what you can do:

• Use multiple workspaces at once. Work with projects across your Webflow workspaces without setting up every connection separately in every AI tool.
• Choose permissions for each project. Give AI read-only access to one website, permission to edit CMS content on another, and broader access to a test project.
• Change permissions in seconds. Adjust access without authorizing the connection again, as long as you stay within the access you’ve already granted in Webflow.
• Open the website or Designer directly. Jump from a project in the app to the place you want to work.
• Choose between Stable and Beta. Select which Webflow MCP version a project uses once you’ve authorized both.
• Connect your AI apps with one click. Set up Codex, Claude Desktop, Claude Code, Cursor, VS Code, or Gemini CLI, then follow the app’s instructions to restart or reload.
• Run it locally, for free. No Kvalifik account, subscription, paid tiers, or locked features.

On Mac, you can also manage projects from the menu bar. And on both Mac and Windows, you can choose to launch MCP Router when you sign in.

Download MCP Router from GitHub.

You choose what AI can do on each project

You might want AI to review one website without changing anything, edit CMS content on another, and have more freedom on a sandbox.

In the default Managed mode, you can choose a permission preset or adjust individual read, write, delete, and publish actions. Read-only is useful for reviewing content. Read & write allows editing while keeping deletion and publishing disabled.

New projects start disabled, so you can review their permissions before making them available to your AI tools.

There’s also an optional Direct Webflow mode for connections if you want to use Webflow’s tools directly. It uses the access authorized in Webflow, and the router’s project switches and granular permissions do not apply. Managed remains the default, and your saved project settings are preserved when you switch back.

My guide to Webflow MCP 2.0 goes into more detail on what AI can do inside Webflow.

Why we’re sharing it

We built the app because we wanted an easier way to use MCP across projects in our Webflow development work. Maybe you’ve run into the same thing.

If it saves someone else the same frustration, that’s a good reason to share it.

The source code is on GitHub, so you can see how the app works, adapt it within the license terms, and contribute improvements. It’s source-available, with a license that allows business use and paid client work. There are restrictions on selling the router or offering its core functionality as a paid service, so check the license if you’re planning to build on it.

We’re interested in how your setup differs from ours. Which AI tools do you use? How many Webflow connections do you need? What still takes more effort than it should?

You don’t need to contribute code to help. A clear description of what you tried and where you got stuck is useful feedback. You can share it on GitHub.

Try it yourself

Getting started takes four steps:

1. Install MCP Router. Download the version for Apple Silicon, Intel Mac, or Windows.
2. Add a Webflow connection. Authorize the sites and workspaces you want to use.
3. Review and enable your projects. Choose the permissions that fit the work.
4. Connect your AI app. Open Apps in MCP Router, select your tool, and follow the restart or reload instructions.

The Mac releases are signed and notarized by Apple and support automatic updates. The Windows build is currently unsigned, so Windows may show a publisher warning during installation. We don’t use Windows in our daily work, so feedback from Windows users is especially useful.

You’ll find installation instructions in the repository and more detail in the setup and permissions guide.

Download MCP Router from the GitHub releases page.

Try it with a project and a task you know well. We’d like to hear how it works for you.