How to Use the Builder MCP in LlamaIndex

Q: How do I index Builder content into a LlamaIndex vector store?

You call listmodelcontent to pull your raw visual blocks and load them into document objects. From there, LlamaIndex parses and embeds the text to make your CMS searchable.

Q: Can a LlamaIndex agent update a Builder visual block?

Yes, the agent uses updatevisualblock to modify layout parameters based on your query. It first checks the index to locate the correct block ID before executing the tool.

Q: How does this MCP Server handle large Builder datasets in LlamaIndex?

The server paginates data through listmodelcontent so your indexer doesn't hit memory limits. You can configure chunk sizes in your LlamaIndex ingestion pipeline to handle thousands of visual blocks.

Index Builder visual blocks and schemas directly into LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Builder MCP to LlamaIndex

Create your Vinkius account to connect Builder 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 Builder with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Builder CMS data for LlamaIndex RAG

The `list_model_content` tool fetches a list of content entries for a specific Builder model. Your LlamaIndex agent executes this tool to pull active layouts and indexes them as document nodes in your vector database. This setup prevents hallucinations by grounding your agent's responses in actual CMS data. The agent checks `get_single_content` to verify live states before suggesting any visual modifications.

Semantic search over Builder models using LlamaIndex

The `search_active_models` tool finds Builder models matching a specific criteria or substring. Your agent runs this tool to locate matching schemas, then retrieves the exact structure using `get_model_schema` to verify if the model fits your current content needs. By using this MCP Server, your LlamaIndex pipeline maps user queries directly to your physical CMS structures. This allows the agent to find the right data model without hardcoded configuration files.

Track media assets within your index

The `get_media_file` tool retrieves details about an uploaded media asset within your Builder space. Your pipeline uses this tool to fetch asset metadata and index the image descriptions alongside your text nodes. You keep your visual assets organized by embedding their metadata directly into your semantic search index. The agent never references broken or missing assets because it verifies them against the index first.

Setup guide

Set up Builder 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 Builder 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 Builder tools.",
)
response = await agent.run("List recent Builder 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 Builder. 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 Builder 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 Builder MCP in LlamaIndex

You call `list_model_content` to pull your raw visual blocks and load them into document objects. From there, LlamaIndex parses and embeds the text to make your CMS searchable.

Yes, the agent uses `update_visual_block` to modify layout parameters based on your query. It first checks the index to locate the correct block ID before executing the tool.

The server paginates data through `list_model_content` so your indexer doesn't hit memory limits. You can configure chunk sizes in your LlamaIndex ingestion pipeline to handle thousands of visual blocks.

Import the basic client, point it to your Vinkius HTTP endpoint, and convert it to a tool spec list. This exposes the MCP tools to your FunctionAgent.

Vinkius runs the server in an isolated, zero-trust sandbox that prevents unauthorized access to your schemas. Your visual blocks and API tokens are never cached on disk, keeping your CMS structure private.

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