You can connect Webflow to Claude in a few minutes using the Model Context Protocol (MCP), and once it’s connected, Claude can read and update your sites, pages, and CMS content without you copying text in and out of the Webflow Designer. Webflow is also one of the more straightforward servers to connect — its OAuth just works with a new client, unlike several other design and productivity tools in this series. This guide covers both ways to do it: Webflow’s official remote MCP server connected directly, and connecting it through a gateway if you use more than one AI client.
What the Webflow MCP server actually does
Webflow publishes an official remote MCP server at mcp.webflow.com/mcp. It exposes your sites, pages, and CMS content as tools Claude can call directly. In practice that means prompts like:
- “List every page on the marketing site and flag which ones haven’t been published in 90 days.”
- “Add a new item to the Blog Posts collection with this title and body.”
- “What CMS fields does the Case Studies collection have?”
- “Update the meta description on the pricing page.”
Claude reads and writes through the same permissions your Webflow account already has — it isn’t a separate export or a static copy of your content, it’s your account acting on your behalf, site by site.
Option 1: Connect Webflow to Claude directly
Claude supports remote MCP servers natively. The short version of the setup:
- Open Claude’s connector or MCP settings.
- Add a remote server pointing at Webflow’s MCP endpoint.
- Sign in with your Webflow account when prompted — this is standard OAuth, so Claude never sees your Webflow password, and you can revoke access from Webflow’s own account settings at any time.
That’s enough for one person using Webflow inside Claude. The tradeoffs show up once you add a second tool or a second person: every additional AI client (ChatGPT, Cursor, an agent) needs its own copy of that same connection, its own OAuth grant, and its own place where the config can go stale or get lost.
Option 2: Connect it once, through a gateway
If you’re already juggling more than one MCP server, or more than one AI client, wiring each pair directly gets old fast — that’s the connection sprawl we wrote about in what an MCP gateway is. The alternative is connecting Webflow (and everything else) to one gateway URL, then pointing every AI client at that single URL instead of reconfiguring each one.
With gate specifically, connecting Webflow looks like this: add gate’s gateway URL to Claude once, then pick Webflow from the Webflow server page in the directory and sign in with OAuth the same way you would directly. From then on, Webflow’s tools are available in every client connected to your gate URL — Claude, ChatGPT, or Cursor — without a second setup step. You can see the full list of servers set up this way on the MCP servers page.
Why the connection method matters for a live website
Webflow isn’t a private database — it’s the thing visitors see. A few things worth checking before or right after you connect:
- Is it the official endpoint? Connect Webflow’s documented server (
mcp.webflow.com), not a third-party mirror claiming to proxy it. - Which sites can it actually reach? An MCP connection to Webflow typically covers every site your account can open, not just the one you had in mind. Know what’s in scope before you hand Claude a broad prompt against “the workspace.”
- What can it write, not just read? A connection with write access can have live pages and CMS content edited or published at whatever pace it’s prompted to. Changes to a published site are visible immediately, so treat write access here with at least as much caution as you would a production deploy.
- Who else on your team can reach it? If more than one teammate connects Webflow to their own AI client, you likely want a shared, revocable setup rather than everyone holding their own token — the same access-control question we cover in MCP access control for teams.
You can run a quick, no-signup check on any server’s tool list — including ones that require OAuth, once connected — with gate’s free MCP security scanner, which looks for prompt injection and hidden instructions in tool descriptions before you rely on a server day to day.
Troubleshooting the connection
A few things that commonly go wrong when connecting any remote MCP server, Webflow included:
- OAuth loop or sign-in fails. Make sure you’re signed into the right Webflow account and workspace in your browser before authorizing — a mismatched workspace is the most common cause.
- Claude can’t find a site you know exists. Webflow’s tools respect your permissions in Webflow itself — if a site lives in a workspace you don’t have access to, Claude won’t see it either.
- Tools disappear after a Webflow update. Remote servers can change their tool list without warning. If you’re connected through a gateway, that kind of change is exactly what drift detection is meant to catch.
The bottom line
Connecting Webflow to Claude with MCP takes a few minutes either way: point Claude directly at Webflow’s server and sign in, or connect it once through a gateway if you want the same Webflow access available in every AI client you use, with the server’s tools checked before they go live. Either way, treat write access to a live site the same way you’d treat any other tool that can change something a visitor sees — worth a minute’s thought before you say yes.