How to Use the Webflow MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK help manage multiple Webflow sites?

You use listsites to pull a list of all accessible Webflow project IDs. From there, your agent can iterate through them. This lets you run deployment or content checks across an entire portfolio using one single workflow.

Q: What is the primary function of publishing sites with the OpenAI Agents SDK?

It executes the final push to make a site public, calling publishsite. Instead of relying on manual steps, your agent performs this action after all content checks and deployments are complete.

Q: Can I list Webflow pages using the OpenAI Agents SDK?

Yes. The listpages tool pulls a comprehensive inventory of every page within a given site. This lets your agent map out all possible URLs for content generation or auditing purposes.

Q: What types of data can the OpenAI Agents SDK read from Webflow?

It reads site details, user information (getuser), and structured CMS data. This includes collection lists, individual items, and page structures.

Automate Webflow deployments safely with OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Webflow to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Publishing and Site Management via MCP Server

The `publish_site` tool lets your agent push a site to production directly. You can also check existing assets by listing sites (`list_sites`) or domains (`list_domains`). This gives your automated workflows the control needed for deployment pipelines. Don't manually hit publish in Webflow. Your system handles this step, ensuring that when a build is ready, it goes live automatically. It’s built into the production agent loop.

CMS Data Operations with OpenAI Agents SDK

Need to manage structured content? Use `list_collections` to see all CMS types and then use `create_collection_item` or `update_collection_item`. These actions let your agent read, write, and modify the actual data points within Webflow. It treats the collection like a database accessible via API. Your specialized agents can now run full content lifecycles—from drafting an article to pushing it into the CMS—all without ever opening the visual editor.

Getting Site Metadata

The `get_site` tool pulls down key details about a specific Webflow project. You can also get granular info using `list_pages` to map out every page URL on a site. This metadata is crucial for building internal inventories of web assets. When your agent needs context—like knowing which pages exist or what the general structure looks like—it uses these tools first. It gives visibility into the entire Webflow environment.

Setup guide

Set up Webflow MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Webflow tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Webflow tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Webflow tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Webflow Agent",
            instructions="You have access to Webflow tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You use `list_sites` to pull a list of all accessible Webflow project IDs. From there, your agent can iterate through them. This lets you run deployment or content checks across an entire portfolio using one single workflow.

It executes the final push to make a site public, calling `publish_site`. Instead of relying on manual steps, your agent performs this action after all content checks and deployments are complete.

Yes. The `list_pages` tool pulls a comprehensive inventory of every page within a given site. This lets your agent map out all possible URLs for content generation or auditing purposes.

It reads site details, user information (`get_user`), and structured CMS data. This includes collection lists, individual items, and page structures.

The server touches non-credentialed site metadata: site domains (`list_domains`), user info via `get_user`, and structured collection item content. It does not touch raw authentication tokens.

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