How to integrate Webflow MCP with OpenAI Agents SDK

GET STARTED FOR FREE
Framework Integration Gradient
Webflow Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Webflow to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Webflow agent that can add a new blog post to my site, list all products in my store collection, get details for order #12345, delete a collection item by its id through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Webflow account through Composio's Webflow MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Webflow
  • Configure an AI agent that can use Webflow as a tool
  • Run a live chat session where you can ask the agent to perform Webflow operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Webflow MCP server, and what's possible with it?

The Webflow MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Webflow account. It provides structured and secure access to your Webflow sites, collections, and e-commerce data, so your agent can perform actions like managing content, updating inventory, handling orders, and retrieving detailed site information on your behalf.

  • Effortless content management: Ask your agent to create, update, or delete collection items—perfect for adding new blog posts, products, or dynamic content without manual entry.
  • Comprehensive site and collection insights: Retrieve up-to-date details about your Webflow sites and collections, including schema, settings, and structure, to power content-aware automations.
  • Inventory and order automation: Have your agent check inventory levels, update stock, and mark orders as fulfilled, streamlining your Webflow e-commerce operations.
  • Bulk data handling: Let your agent list all items in a collection or all collections on a site, enabling smart reporting, audits, or content migrations with a simple prompt.
  • Seamless integration with creative workflows: Enable real-time, AI-driven updates to your site content, inventory, or orders in response to team or customer needs—no coding required.

Supported Tools & Triggers

Tools
Create Webflow Collection ItemThis tool creates a new item in a specified webflow collection.
Delete Webflow Collection ItemThis tool allows you to delete a specific item from a collection in webflow.
Fulfill OrderThis tool allows you to mark an order as fulfilled in webflow's e-commerce system.
Get Collection DetailsRetrieves a specific collection by its id from a webflow site.
Get Collection ItemThis tool retrieves a specific item from a webflow collection.
Get Item InventoryThis tool retrieves the current inventory levels for a specific item in a webflow collection.
Get Order DetailsThis tool retrieves detailed information about a specific order in webflow.
Get Webflow Site InformationThis tool retrieves detailed information about a specific webflow site.
List Collection ItemsThis tool retrieves a list of items from a specified collection in webflow.
List Webflow CollectionsThis tool retrieves a list of all collections for a given webflow site.
List Form SubmissionsThis tool retrieves a list of form submissions for a specific webflow site.
List Webflow OrdersThis tool retrieves a list of all orders for a specified webflow site using the get /sites/{site id}/orders endpoint.
List PagesThis tool retrieves a list of all pages for a specified webflow site.
List Webflow SitesThis tool retrieves a list of all webflow sites accessible to the authenticated user.
Publish Webflow SiteThis tool publishes a webflow site, making all staged changes live.
Refund OrderThis tool allows you to refund a webflow e-commerce order.
Unfulfill OrderThis tool allows you to mark a previously fulfilled order as unfulfilled in webflow.
Update Webflow Collection ItemThis tool allows updating an existing item in a webflow collection using the patch /collections/{collection id}/items/{item id} endpoint.
Update Item InventoryThis tool allows you to update the inventory levels of a specific sku item in your webflow e-commerce site by either setting the inventory quantity directly or updating it incrementally.
Update OrderThis tool allows updating specific fields of an existing order in webflow.
Upload Asset to WebflowThis tool allows users to upload assets (files, images, etc.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Webflow project
  • Some knowledge of Python or Typescript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Webflow.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Webflow Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["webflow"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only webflow.
  • The router checks the user's Webflow connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Webflow.
  • This approach keeps things lightweight and lets the agent request Webflow tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Webflow. "
        "Help users perform Webflow operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Webflow and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Webflow operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Webflow.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Webflow and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["webflow"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Webflow. "
        "Help users perform Webflow operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Webflow MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Webflow.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Webflow MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Webflow MCP with Claude Agent SDK

Google ADK

Google ADK

Use Webflow MCP with Google ADK

LangChain

LangChain

Use Webflow MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Webflow MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Webflow MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Webflow MCP with LlamaIndex

CrewAI

CrewAI

Use Webflow MCP with CrewAI

Claude Code

Claude Code

Use Webflow MCP with Claude Code

FAQ

What are the differences in Tool Router MCP and Webflow MCP?

With a standalone Webflow MCP server, the agents and LLMs can only access a fixed set of Webflow tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Webflow and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Webflow tools.

Can I manage the permissions and scopes for Webflow while using Tool Router?

Yes, absolutely. You can configure which Webflow scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Webflow data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free