Summary
Connects Claude to Webflow's CMS and site management capabilities through Pipeworx's gateway infrastructure. The server is part of a larger platform offering 728+ data sources, but can be used standalone for Webflow-specific operations. Configuration is straightforward with streamable HTTP transport, and you can either call tools directly or use the ask_pipeworx natural language interface to query Webflow data without dealing with specific API parameters. Useful when you're building workflows that need to read or manipulate Webflow collections, manage sites, or integrate CMS content into AI-driven processes. The source doesn't list specific tools, so check the Pipeworx documentation for the full catalog of available Webflow operations.
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
mcp-webflow
Webflow MCP Pack
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Tools
| Tool | Description |
|---|---|
list_sites | List all Webflow sites accessible to the connected account. Returns each site's id, display name, short name, preview URL, last published time, and custom domains. Use to discover which Webflow sites are available before reading their CMS collections or site content. |
get_site | Get metadata for a single Webflow site by its id, including display name, short name, preview URL, time zone, last published time, and custom domains. Use after list_sites to inspect a specific site before browsing its CMS collections and content. |
list_collections | List the CMS collections defined on a Webflow site. Returns each collection's id, display name, slug, singular name, created time, and last updated time. Use to discover the CMS structure of a site before listing or reading collection items (the actual site content). |
list_collection_items | List the items (records) in a Webflow CMS collection — the live site content such as blog posts, products, or team members. Returns paginated items with their id, draft/archived status, last published time, and fieldData (the CMS field values). Use to read the actual content stored in a Webflow collection. |
get_collection_item | Get a single item (record) from a Webflow CMS collection by its id. Returns the item's id, draft/archived status, last published time, and fieldData (the full CMS field values). Use after list_collection_items to read one piece of Webflow site content in detail. |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"webflow": {
"url": "https://gateway.pipeworx.io/webflow/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/webflow/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Webflow data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
No MCP client? Call it over HTTP
This pack runs against a connected webflow account, so it needs a Pipeworx key: sign in at https://pipeworx.io/account, connect webflow, then call POST https://gateway.pipeworx.io/v1/tools/list_sites with Authorization: Bearer <your Pipeworx key>. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/list_sites. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Featured
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →