How do I get my Webflow API token?

Log in to your Webflow Dashboard. Open the site you want to connect and click the **gear icon** to access Site Settings. In the left sidebar, click **Apps & integrations**. Scroll to the **API access** section at the bottom and click **Generate API token**. Name your token, select the required permission scopes (e.g., CMS read/write, Sites publish), and click **Generate token**. Copy it immediately — Webflow will not show the full token again. Each site can have up to 5 tokens. Tokens expire aft

Can my AI agent publish a blog post to my Webflow site?

Yes. Your AI agent can create CMS collection items (like blog posts), set all fields including title, body, slug, thumbnail, and publish date, then trigger a site publish — all in one conversation. Perfect for content teams who want to skip the Webflow designer and go from draft to live in seconds.

What if I manage multiple client sites as an agency?

Each Webflow site has its own API token, so you can configure multiple integrations — one per client site. This lets your AI agent switch between projects, bulk-update CMS content across sites, or publish changes to specific client domains without mixing data between accounts.

Can I track e-commerce orders through my AI agent?

Yes. If you use Webflow's built-in e-commerce, your AI agent can retrieve orders, order details, fulfillment statuses, and product inventory — giving you a real-time view of sales activity without opening the Webflow dashboard or exporting reports.

Webflow MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Webflow
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Webflow through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Webflow Assistant",
            instructions=(
                "You help users interact with Webflow. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Webflow"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Webflow MCP Server

Connect Webflow to your AI agent and manage your websites, CMS content, and e-commerce data conversationally.

The OpenAI Agents SDK auto-discovers all 10 tools from Webflow through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Webflow, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

CMS Management — List, create, update, and delete CMS collection items (blog posts, portfolio entries, product listings) from natural language.
Site Publishing — Trigger site publishes and check publish status across staging and production domains.
Collection Schema — Query collection structures, field types, and validation rules to understand your content model.
E-commerce Data — Retrieve orders, products, and inventory data from Webflow's built-in e-commerce engine.

The Webflow MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Webflow to OpenAI Agents SDK via MCP

Follow these steps to integrate the Webflow MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Webflow

Why Use OpenAI Agents SDK with the Webflow MCP Server

OpenAI Agents SDK provides unique advantages when paired with Webflow through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Webflow + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Webflow MCP Server delivers measurable value.

Automated workflows: build agents that query Webflow, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Webflow, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Webflow tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Webflow to resolve tickets, look up records, and update statuses without human intervention

Webflow MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Webflow to OpenAI Agents SDK via MCP:

create_collection_item

Create a CMS item

get_site

Get site details

get_user

Get authorized user info

list_collection_items

List items in a collection

list_collections

List CMS collections

list_domains

List site domains

list_pages

List all site pages

list_sites

List all Webflow sites

publish_site

Publish site to production

update_collection_item

Update a CMS item

Example Prompts for Webflow in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Webflow immediately.

"List all blog posts in my Webflow CMS."

"Publish my Webflow site to production."

"Create a new blog post titled 'How AI Transforms Marketing'."

Troubleshooting Webflow MCP Server with OpenAI Agents SDK

Common issues when connecting Webflow to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Webflow + OpenAI Agents SDK FAQ

Common questions about integrating Webflow MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.