How to Use the Webflow MCP in LlamaIndex

Q: How do I use Webflow and LlamaIndex together?

The process is: first, call a tool like getsite to get current data. Then, the output of that API call gets indexed into your vector store. Your agent can then query this knowledge base for answers later.

Q: Can Webflow and LlamaIndex help me manage CMS items?

Yes. When you run createcollectionitem or updatecollectionitem, the resulting data is immediately indexed. This means your knowledge base remembers exactly what content was added, making it retrievable for future queries.

Q: If I need Webflow and LlamaIndex for publishing?

You can index successful publish events using publishsite. If a query comes in about the deployment status or history of a site, your agent pulls that information from the indexed knowledge base.

Q: What if I need Webflow and LlamaIndex for user context?

Call getuser to get the latest authorized info. This raw data gets stored in the index, meaning you can later query historical sessions about that specific user's permissions or actions.

Build RAG search engines for Webflow with LlamaIndex. Index API data into your knowledge base.

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 LlamaIndex

Create your Vinkius account to connect Webflow to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Querying Site Configurations

LlamaIndex lets you index live site details. Instead of just running `get_site`, the output becomes a searchable document in your vector store. You can query, 'What are the domains associated with this user?' and get an answer grounded in actual data. This mechanism makes every call to `list_domains` part of your knowledge base. It’s perfect for building systems that need historical context or complex cross-referencing.

Tracking CMS Changes

Need to know what changed? Use the MCP Server's tools—like `list_collection_items` and `update_collection_item`—and index those results. You can then ask, 'Show me all collections that were updated last week.' The AI client reads this indexed data for semantic search, not just a direct API response. It turns raw CMS activity into searchable knowledge.

Analyzing Webflow Project Scope

You can index the full structure of a site by combining `list_sites` and `list_pages`. Your agent doesn't just list them; it creates an indexed map of every accessible page and project. This allows you to ask complex questions like, 'Which collections are linked across all sites in this domain group?' The knowledge base handles the complexity for you.

Setup guide

Set up Webflow MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Webflow MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Webflow tools.",
)
response = await agent.run("List recent Webflow data")

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 LlamaIndex

The process is: first, call a tool like `get_site` to get current data. Then, the output of that API call gets indexed into your vector store. Your agent can then query this knowledge base for answers later.

Yes. When you run `create_collection_item` or `update_collection_item`, the resulting data is immediately indexed. This means your knowledge base remembers exactly what content was added, making it retrievable for future queries.

You can index successful publish events using `publish_site`. If a query comes in about the deployment status or history of a site, your agent pulls that information from the indexed knowledge base.

Call `get_user` to get the latest authorized info. This raw data gets stored in the index, meaning you can later query historical sessions about that specific user's permissions or actions.

It touches all structural and content data: site metadata (domains), CMS items, user credentials, and the historical state of those collections.

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