How to Use the Webflow MCP in Google ADK

Q: How can I process Webflow content using the Google ADK?

You use tools like listcollectionitems to pull structured data into BigQuery. The agent reads this web data, runs complex analysis in Vertex AI, and writes reports back to your cloud storage.

Q: Can I update Webflow content using the Google ADK?

Yes. The updatecollectionitem tool lets your agent modify existing CMS records. This is key for automated workflows that correct or enrich data before it gets analyzed in BigQuery.

Q: What specific Webflow domains can the Google ADK list?

The listdomains tool retrieves all registered site domain names associated with your Webflow account. This gives you a clean inventory of all web properties managed through this MCP Server.

Connect Webflow assets to BigQuery using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Webflow MCP to Google ADK

Create your Vinkius account to connect Webflow to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Webflow with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Webflow CMS Data Integration with Google ADK

The `list_collection_items` tool lets your agent pull bulk data from a Webflow CMS collection. This structured content flows naturally into BigQuery for deep analysis using Vertex AI. Your agents treat the CMS as an API endpoint feeding enterprise data. The ability to list all collections (`list_collections`) first helps structure exactly what you're going to push to your cloud warehouse.

Webflow Site Structure Audits with Google ADK

You can map out an entire web presence using `list_sites` and then drill down into specific assets. The `get_site` tool retrieves core site details needed to populate metadata tables in BigQuery. This makes Webflow data actionable within your existing GCP environment. It's designed for large-scale operations; the agent can process these web asset lists alongside other enterprise records.

Publishing and User Context with MCP Server

The `publish_site` tool allows your workflow to trigger a production deployment, which is critical for continuous integration. Additionally, using `get_user` lets the agent know who is running the process. This provides necessary context when logging actions into BigQuery. This mechanism ensures that every change—whether publishing or updating an item via `update_collection_item`—is traceable and attributable in your data lake.

Setup guide

Set up Webflow MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Webflow tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Webflow_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Webflow tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Webflow. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Webflow now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Webflow MCP in Google ADK

You use tools like `list_collection_items` to pull structured data into BigQuery. The agent reads this web data, runs complex analysis in Vertex AI, and writes reports back to your cloud storage.

It gives your agent a full inventory of every project you manage. Your workflows can then process site-specific actions, like checking status or pulling metadata, across dozens of separate web projects.

Yes. The `update_collection_item` tool lets your agent modify existing CMS records. This is key for automated workflows that correct or enrich data before it gets analyzed in BigQuery.

The `list_domains` tool retrieves all registered site domain names associated with your Webflow account. This gives you a clean inventory of all web properties managed through this MCP Server.

It touches structured content (CMS items), site details, and user identification info. All these are raw textual or object-based data types ready for ingestion into BigQuery.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript