How to Use the Webflow MCP in CrewAI

Q: How do I list all Webflow pages with CrewAI?

You create a specialized task. One agent uses listpages to gather every page name and URL. The result is then shared with the moderator agent for review or action.

Coordinate Webflow Operations with CrewAI's Multi-Agent Teams.

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 CrewAI

Create your Vinkius account to connect Webflow to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized Content Management Teams

Don't run one agent—run a team. You can assign Agent A to research site inventory using `list_collections`, and Agent B to analyze that data by calling `get_site`. The shared memory ensures the findings are passed correctly between roles. This setup is perfect for multi-step content audits across your entire Webflow presence.

Autonomous Publishing Pipelines

Need a site updated and live? You set up a crew where one agent drafts the changes (`update_collection_item`), a second validates them, and a third executes `publish_site`. The monitor agent keeps an eye on the whole process. This collaborative structure handles complex, multi-stage operations that require high coordination.

Comprehensive Webflow Site Discovery

Build a discovery crew. Agent 1 lists all domains using `list_domains`. Agent 2 then takes those results and calls `list_pages` for each one, consolidating the data. This is structured role-based analysis. The entire operation is autonomous, letting you discover every asset without human intervention.

Setup guide

Set up Webflow MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Webflow tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Webflow Analyst",
    goal="Access and analyze Webflow data via MCP.",
    backstory="Expert analyst with direct Webflow access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Webflow transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Webflow Analyst",
        goal="Access and analyze Webflow data via MCP.",
        backstory="Expert analyst with direct Webflow access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Webflow transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign the MCP Server to a crew. One agent can be specialized in deployment, calling `publish_site` after another agent has gathered all necessary site data via `list_sites`.

Yes. You designate a specific agent to handle content writes using `update_collection_item`. This specialized action allows the crew to modify records reliably based on shared memory findings.

The server touches site and user metadata, specifically accessing `site details`, `user info` (via `get_user`), and all collection content via `collection items`. This is the scope for your agent team.

You create a specialized task. One agent uses `list_pages` to gather every page name and URL. The result is then shared with the moderator agent for review or action.

It works great. Since you're building autonomous operations, having access to tools like `list_collections` and `get_site` lets your crew perform complex, multi-step tasks without needing a human prompt for every single step.

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