Webflow MCP Server

Webflow’s official MCP server for AI-assisted website design, CMS management, and content work on a live project.

Description

The Webflow MCP Server is Webflow’s official interface that lets an MCP-capable AI client work directly with Webflow projects. Instead of handling design, CMS content, and page structure exclusively by hand in the Webflow Designer, an agent inside Cursor, Claude Desktop, Claude Code, or another compatible client can connect to a Webflow account and carry out tasks described in natural language. According to the provider, this covers responsive layouts built from sections, containers, and grids, individual elements such as rich text, buttons, forms, and media, plus CSS classes, combo classes, and raw CSS. Reusable components with props, variants, and slots, custom code, custom fonts, and design-system variables for color schemes are also part of the documented feature set.

Beyond visual design, the server covers content management: CMS collections and fields including bulk updates, pages, assets, forms, the sitemap, SEO metadata, and comments can all be read and edited through the agent. Webflow also offers Analyze capabilities that surface sessions, users, pageviews, top pages, and traffic sources through chat — according to Webflow, this analytics add-on requires a paid site plan and is not included with every account.

Two access paths, one repository

Webflow publishes the server in the official webflow/mcp-server repository (MIT license, TypeScript, exactly 140 GitHub stars via the API on September 21, 2026) and offers two ways to run it. The recommended path is the hosted remote server at https://mcp.webflow.com/sse: authentication happens through OAuth, no local API token is needed, and for Designer-specific features like visual snapshots or canvas navigation, Webflow automatically installs a companion “MCP Bridge App” into the workspace during authorization. Alternatively, the server can run locally via the webflow-mcp-server npm package through npx; this requires a self-registered Webflow app and a personal API token supplied through the WEBFLOW_TOKEN environment variable. Both paths require Node.js 22.3.0 or newer. This entry treats both official paths as one server (deployment_type = both) because they ship from the same repository and expose the same tools.

MCP 2.0 and the role of the bridge app

In August 2026, Webflow rolled out what its own announcement calls “MCP 2.0”: the earlier requirement to run the bridge app was removed “for most use cases,” which allows working on several pages at once and is meant to make workflows more reliable. New additions include full access to design-system components with props, slots, and variants, centrally stored “Agent Instructions” for tone, design, and compliance guidance, full enforcement of team roles and permissions including branching, and a complete audit trail of changes with AI attribution in the Activity Log. According to the provider, MCP 2.0 is “available on all site plans, at no additional cost” — so baseline use is not tied to a specific paid plan, even though certain analytics features still require a separate, paid add-on.

Governance built on existing permissions

Webflow deliberately describes its permission model as tied to existing user rights: an agent using the MCP server can only do what the connected account could already do inside the Webflow Designer, nothing more. This role-based access control sits on top of OAuth authorization and is reinforced by the Activity Log, which keeps changes — including AI authorship — traceable. For teams, this is an important difference from MCP servers that grant blanket access to an entire account: someone who can only edit specific pages or collections in the Designer cannot use an agent to go beyond that boundary.

Who benefits from the Webflow MCP Server

The server suits anyone already building or maintaining websites in Webflow who wants to handle recurring work — new CMS entries, structural or copy changes, SEO metadata, linking older blog posts, or drafting new sections — through a prompt instead of manual clicking. For teams that take governance seriously, it matters that Designer permissions carry over one-to-one and that every change is logged. Anyone looking for a fully independent headless CMS with no tie to the Webflow design surface may be better served by generic REST/GraphQL access through the Webflow Data API than by this Designer-oriented MCP toolkit.

Security, data flow, and limits

Webflow projects can contain content from other people — form submissions, CMS entries sourced externally, or comments — that may end up in prompts or tool results. Such content should be treated as untrusted text, not as an instruction to the agent. Tool results pass through the connected AI client and may be processed by that client’s model provider; before sensitive customer data, credentials, or unpublished content are involved, it is worth checking the data policies of the client and model in use. For production sites, it is advisable to test write actions on non-critical pages or in a staging setup first and to review changes in the Activity Log before they go live. When running locally with WEBFLOW_TOKEN, treat that token like any other API secret and avoid sharing it in plain text.

Requirements

An MCP-compatible AI client (e.g. Cursor or Claude Desktop), a Webflow account with access to the target project, and for local use Node.js 22.3.0 or newer plus a Webflow API token.

Installation instructions

Quick start

Remote (recommended): add https://mcp.webflow.com/sse as an MCP server in the client configuration and complete the OAuth flow; Webflow automatically installs the MCP Bridge App. Local: register your own Webflow app, set WEBFLOW_TOKEN, and configure npx -y webflow-mcp-server@latest as the command in the MCP configuration.

bash
npx -y webflow-mcp-server@latest

Step 1: Decide before setup: remote or local

Webflow offers the MCP server in two official variants. For most cases, the hosted remote server at https://mcp.webflow.com/sse is the better choice: it needs no local installation and handles authentication through OAuth. The local variant, distributed as the webflow-mcp-server npm package, is worth using mainly when you need a custom Webflow app with specific permissions or when an OAuth flow isn’t possible on your network. Node.js 22.3.0 or newer is required either way.

In Cursor, add the server to .cursor/mcp.json:

json
{
  "mcpServers": {
    "webflow": { "url": "https://mcp.webflow.com/sse" }
  }
}

In Claude Desktop, the connection runs through the mcp-remote bridge process in claude_desktop_config.json:

json
{
  "mcpServers": {
    "webflow": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.webflow.com/sse"]
    }
  }
}

After saving, the client automatically opens an OAuth login page. Sign in with your Webflow account there and authorize access to the sites you want to work with. Then, in the Webflow Designer, open the Apps panel (press E) and launch the published “Webflow MCP Bridge App”; it connects the active Designer session to the MCP server for features like visual snapshots or canvas navigation.

Step 3: Set up the local server (alternative)

For local operation, first register your own Webflow app in the workspace and publish the corresponding MCP bridge app in the Designer (see the official “Register an App” documentation for details). Then add this to your client’s MCP configuration:

json
{
  "mcpServers": {
    "webflow": {
      "command": "npx",
      "args": ["-y", "webflow-mcp-server@latest"],
      "env": { "WEBFLOW_TOKEN": "<YOUR_WEBFLOW_TOKEN>" }
    }
  }
}

Generate the required API token through Webflow’s API Playground. Treat it like any other access secret: don’t share it in plain text and don’t commit it to a public repository.

Step 4: Verify the connection with a read task

Before letting the agent make write changes, verify the connection with a harmless read request, such as: “List the last five blog posts on this site.” Once the expected project is correctly recognized, tasks like creating a new section, adding SEO metadata, or linking older posts become reasonable next steps. Review every change afterward in the Webflow Activity Log, which the provider says also documents AI authorship.

Governance and team permissions

The agent can only do what the connected account could already do in the Designer. For teams with different roles, this means someone who can only edit specific pages or CMS collections cannot use the MCP server to go beyond that boundary. In Enterprise workspaces, an administrator must also enable MCP access before individual members can use it.

FAQ

Do I need a paid Webflow plan? According to the provider, MCP 2.0 is available on all site plans at no additional cost. Only the optional Webflow Analyze add-on requires a paid plan.

What exactly does the MCP Bridge App do? It connects an active Webflow Designer session to the MCP server and is needed for Designer-specific features like visual snapshots or canvas navigation. On the remote path, Webflow installs it automatically during OAuth authorization.

Can I use the remote and local server at the same time? This isn’t officially documented and should be avoided to prevent duplicate tools and separate sessions. Pick one path per client.

What do the 140 GitHub stars cover? The entire webflow/mcp-server repository, which provides both the remote and local paths; retrieved via the GitHub API on September 21, 2026.

How do I limit risk on sensitive sites? Test write actions on non-critical pages first, use an account with only the permissions you need, and review changes in the Activity Log regularly.

npx -y webflow-mcp-server@latest

Authentication

Remote server: OAuth authorization on connect. Local operation: a personal Webflow API token supplied via the WEBFLOW_TOKEN environment variable.

Required access permissions

According to the provider, an agent using the MCP server can only do what the connected account could already do in the Webflow Designer itself; team roles and permissions are fully enforced.

Transmitted or stored data

The server returns project, CMS, and analytics data to the connected AI client, which may forward results to its model provider; review that provider’s data policy separately. All changes are logged in the Webflow Activity Log with AI attribution.

Security risks

Project content (forms, CMS entries, comments) can contain untrusted text. Test write actions on non-critical pages first, treat the local WEBFLOW_TOKEN like any secret, and review changes in the Activity Log.

License and costs

License
MIT
Cost
free

According to the provider, MCP 2.0 is available on all Webflow site plans at no additional cost; the optional Webflow Analyze add-on requires a paid site plan. Check current details on the official Webflow pricing pages.

Alternatives

Not recorded yet.

At a glance

Provider
Webflow
Status
Official server
Deployment
Local and remote
Current version
1.0.1
GitHub stars
141
Last reviewed
21.09.2026

Repository and documentation

Categories

Supported clients

Not recorded yet.