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

Q: How do I connect LangChain to Kentico (CMS & DXP)?

Use MultiServerMCPClient with the Vinkius endpoint. Call client.gettools() and pass the array to your ReAct agent.

Q: Can LangChain agents update Kentico (CMS & DXP) documents?

Yes. The agent uses getsitedocument to read the current text, modifies it in memory, and writes it back using updatesitedocument.

Q: How does LangSmith trace Kentico (CMS & DXP) tool calls?

Every execution of listsystemobjects or getuser logs the exact input parameters and the JSON response. You see latency and token usage for every API interaction.

Q: Can I chain Kentico user data with other tools?

You extract profiles with listusers and pipe the resulting array into your next tool. The output of the Kentico read becomes the input for your database write.

Build multi-step reasoning pipelines that manage Kentico (CMS & DXP) content directly through LangChain 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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Content Management Chains

The `get_site_document` tool feeds live CMS pages directly into your LangChain workflow. Your agent reads the current state of a webpage, evaluates it against your prompt instructions, and determines what needs fixing. Once the agent decides on the edits, it calls `update_site_document` to push those changes back to the CMS. You build pipelines that automatically fix formatting, update pricing, or translate copy without manual data entry.

LangChain MCP Server Audits

The `list_system_objects` tool gives your agent a complete view of roles, page templates, and configurations. You pipe this list into a formatting node or directly to another agent for evaluation. If an object requires closer inspection, the agent triggers `get_single_object` with the specific ID. The MCP Server handles the REST communication, returning the exact JSON needed for the next step in your ReAct loop.

User and Table Data Pipelines

You pull active accounts using the `list_users` tool and pass the output into a LangSmith-traced validation chain. The agent checks email domains or permission levels against your business rules. For custom data structures, `list_custom_table_rows` extracts specific records like ecommerce transactions or form submissions. The agent processes this data, making it available for downstream tools or external database syncs.

Setup guide

Set up Kentico (CMS & DXP) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kentico (CMS & DXP) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kentico-cms-dxp-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kentico (CMS & DXP) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Use `MultiServerMCPClient` with the Vinkius endpoint. Call `client.get_tools()` and pass the array to your ReAct agent.

Yes. The agent uses `get_site_document` to read the current text, modifies it in memory, and writes it back using `update_site_document`.

Every execution of `list_system_objects` or `get_user` logs the exact input parameters and the JSON response. You see latency and token usage for every API interaction.

You extract profiles with `list_users` and pipe the resulting array into your next tool. The output of the Kentico read becomes the input for your database write.

Vinkius routes your requests through a V8 Isolate Sandbox. When `get_user` or `get_site_document` pulls user emails and CMS text, the data exists only for the duration of the tool call. The environment is entirely ephemeral and destroys itself after execution.

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