How to Use the Constructor MCP in LlamaIndex

Q: How do I index Constructor product data in LlamaIndex?

Use the searchproducts tool to fetch CRM records from the Headless Constructor.io platform. LlamaIndex indexes these records as document nodes, making them searchable via semantic queries.

Q: Can LlamaIndex query Constructor search pagination via MCP?

Yes, LlamaIndex uses the searchpagination tool to fetch Gateway history. The framework parses this historical data to build a temporal index of past customer searches.

Q: How does LlamaIndex handle Constructor brand arrays?

The framework calls the browsebrand tool to inspect internal arrays mitigating plan math. LlamaIndex stores these arrays as metadata to help filter search queries by specific brand rules.

Q: Can I filter search results by color?

Yes. The searchfiltered tool restricts product arrays to exact colors or sizes, returning clean JSON structures directly to the query engine.

Index Constructor search logs and customer bindings into LlamaIndex vector stores with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Constructor MCP to LlamaIndex

Create your Vinkius account to connect Constructor 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 Constructor with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Constructor customer bindings into LlamaIndex

The `browse_category` tool provisions a high-availability JSON payload that generates hard customer bindings for your LlamaIndex knowledge base. Your pipeline indexes these bindings directly into vector stores to ground future queries in actual user permissions. This setup prevents your RAG system from recommending products that the customer cannot access. LlamaIndex queries this indexed payload to verify visibility rules before generating any product lists.

Audit platform limits inside LlamaIndex

The `get_recommendations` tool retrieves explicit cloud logging tracing explicit vault limits directly into your LlamaIndex query engine. By indexing these logs, your agent learns the exact thresholds of your recommendation engine without hitting API limits repeatedly. The framework treats these logged limits as semantic documents, allowing your agent to search past threshold warnings. This ensures your application stays within operational limits during peak traffic.

Filter search arrays with this MCP Server

The `search_filtered` tool restricts product arrays to exact colors, sizes, or features by bounding JSON structures directly in the active index. Your LlamaIndex agent feeds these filtered structures into its retriever to narrow down search results before synthesizing responses. This direct integration bypasses standard post-processing steps, reducing latency by 40 milliseconds per query. Your agent delivers precise product matches based on structured e-commerce attributes.

Setup guide

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

Use the `search_products` tool to fetch CRM records from the Headless Constructor.io platform. LlamaIndex indexes these records as document nodes, making them searchable via semantic queries.

Yes, LlamaIndex uses the `search_pagination` tool to fetch Gateway history. The framework parses this historical data to build a temporal index of past customer searches.

The framework calls the `browse_brand` tool to inspect internal arrays mitigating plan math. LlamaIndex stores these arrays as metadata to help filter search queries by specific brand rules.

Yes. The `search_filtered` tool restricts product arrays to exact colors or sizes, returning clean JSON structures directly to the query engine.

This MCP Server processes all CRM records in an ephemeral V8 sandbox on Vinkius. No customer data or search logs are stored on disk, and memory is wiped immediately after LlamaIndex finishes indexing the payload.

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