How to Use the Webflow MCP in Pydantic AI

Q: Can I manage site assets using Webflow and Pydantic AI?

Yes, the agent can list all uploaded assets via listsiteassets. The data is validated upon retrieval, so you trust the inventory count completely.

Q: How do I check for existing sites using Webflow and Pydantic AI?

You call listsites to get a list of all available projects. The resulting data structure is validated, so you know exactly what fields to expect when checking project existence.

Q: What services are included in the MCP Server for Webflow?

The server provides tools ranging from listsiteusers and listecommerceorders to core functions like listing assets and getting site details. It's a robust set of capabilities.

Type-Safe Webflow Actions with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Webflow to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track E-commerce Orders via MCP Server

You use `list_ecommerce_orders` to get a structured list of all sales records. Because of the Pydantic validation, you'll know exactly which fields are present and what type they should be—no corrupted data. Need more context? The agent can also list specific CMS collection items using `list_collection_items`, ensuring every field is correct before processing.

Build Webflow Content Safely

The framework validates your calls to `create_collection_item`. If the API sends back an unexpected data format, your agent fails loud with a validation error. This prevents silent corruption of content. Before building anything, check what collections exist using `list_cms_collections` to ensure you're targeting the right structure.

Get Site and User Details

Use `get_site_details` when you need verified metadata for one site. The Pydantic layer confirms that all returned details match your expected model, giving you high confidence in the data. Furthermore, it validates user lists by calling `list_site_users`, confirming every field related to a registered account is correct.

Setup guide

Set up Webflow MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "webflow-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Webflow tools.",
)

result = await agent.run("List recent Webflow transactions")
print(result.output)

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 Pydantic AI

Every single response from the MCP Server—whether it's asset listings or order details—is validated against a defined Pydantic model. This guarantees high type-safety.

Yes, the agent can list all uploaded assets via `list_site_assets`. The data is validated upon retrieval, so you trust the inventory count completely.

You call `list_sites` to get a list of all available projects. The resulting data structure is validated, so you know exactly what fields to expect when checking project existence.

The server provides tools ranging from `list_site_users` and `list_ecommerce_orders` to core functions like listing assets and getting site details. It's a robust set of capabilities.

This server touches e-commerce order records, user registration details (site users), and CMS collection items. The Pydantic validation ensures correct handling of these structured data types.

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