How to Use the Kentico (CMS & DXP) MCP in LlamaIndex

Q: How do I configure LlamaIndex for Kentico (CMS & DXP)?

Install llama-index-tools-mcp and instantiate a BasicMCPClient with your Vinkius URL. Pass the client to McpToolSpec to generate the tool list.

Q: Can I index Kentico (CMS & DXP) documents into my LlamaIndex vector store?

You run getsitedocument to fetch the content. LlamaIndex automatically processes the returned JSON into standard Document objects for embedding.

Q: Does LlamaIndex support querying Kentico (CMS & DXP) custom tables?

Yes. The listcustomtablerows tool outputs tabular data that you map into your index. This makes custom ecommerce data available for semantic search.

Q: How often should I re-index Kentico system objects?

You control the polling frequency. Run listsystemobjects on a cron job to refresh your vector store whenever templates or roles change.

Q: What happens to my Kentico custom table data during MCP queries?

The architecture relies on zero-trust execution. When listcustomtablerows fetches your ecommerce records, Vinkius processes the request in a stateless container. No data persists on the server after the response hits your local index.

Turn your Kentico (CMS & DXP) databases into searchable vector knowledge bases using LlamaIndex and 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 Kentico (CMS & DXP) MCP to LlamaIndex

Create your Vinkius account to connect Kentico (CMS & DXP) 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 Kentico (CMS & DXP) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing CMS Documents

The `get_site_document` tool extracts raw text and metadata from your Kentico instance. LlamaIndex takes this output, chunks the content, and embeds it into your vector store. Your agents now answer questions based on actual published content rather than guessing. When a user asks about a specific product policy, the agent queries the index and retrieves the exact document section.

LlamaIndex MCP Server Data

You pull structured ecommerce records using the `list_custom_table_rows` tool. The MCP Server returns the raw table data, which LlamaIndex converts into queryable nodes. This allows your RAG application to perform semantic searches over custom Kentico tables. You stop writing complex SQL queries and start asking plain-text questions about your stored metrics.

System Configuration Queries

The `list_system_objects` tool pulls your entire Kentico setup, including roles and templates. You index this configuration state so developers can query the architecture directly. If the index requires deeper context on a specific template, LlamaIndex triggers `get_single_object`. The resulting data updates the vector store, giving your team an always-accurate, searchable map of the CMS backend.

Setup guide

Set up Kentico (CMS & DXP) 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 Kentico (CMS & DXP) 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 Kentico (CMS & DXP) tools.",
)
response = await agent.run("List recent Kentico (CMS & DXP) 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 Kentico Xperience. 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 Kentico (CMS & DXP) 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 Kentico (CMS & DXP) MCP in LlamaIndex

Install `llama-index-tools-mcp` and instantiate a `BasicMCPClient` with your Vinkius URL. Pass the client to `McpToolSpec` to generate the tool list.

You run `get_site_document` to fetch the content. LlamaIndex automatically processes the returned JSON into standard Document objects for embedding.

Yes. The `list_custom_table_rows` tool outputs tabular data that you map into your index. This makes custom ecommerce data available for semantic search.

You control the polling frequency. Run `list_system_objects` on a cron job to refresh your vector store whenever templates or roles change.

The architecture relies on zero-trust execution. When `list_custom_table_rows` fetches your ecommerce records, Vinkius processes the request in a stateless container. No data persists on the server after the response hits your local index.

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