How to Use the Kentico (CMS & DXP) MCP in OpenAI Agents SDK

Q: How do I connect Kentico (CMS & DXP) to OpenAI Agents SDK?

Install openai-agents via pip. Initialize the connection using MCPServerStreamableHttp with your Vinkius endpoint, then pass the server instance inside the mcpservers list when instantiating your Agent.

Q: How does the Kentico (CMS & DXP) toolset handle high-traffic API calls in OpenAI Agents SDK?

Set cacheToolsList=True in your connection parameters. This prevents the agent from making redundant schema discovery requests every time it needs to call getsitedocument or list users.

Run production-ready OpenAI Agents SDK workflows that manage Kentico CMS pages and users with built-in safety guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Kentico (CMS & DXP) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Kentico updates inside OpenAI Agents SDK

The `update_site_document` tool lets your production OpenAI Agents SDK workflows edit live Kentico CMS pages with strict guardrails. This MCP Server exposes the tool directly to your agentic workflows, letting OpenAI's reasoning engine check structural edits before they hit your live site. You get complete execution tracing on the OpenAI dashboard for every Kentico document update. If an agent tries to modify a template, the platform intercepts and validates the change, ensuring your CMS data stays clean.

Sync users and system objects programmatically

The `list_users` tool lets you run background tasks that audit your Kentico setup using this MCP integration. The agent uses this alongside `get_user` to check permissions, then triggers `update_system_object` to align roles. By caching tool definitions with `cacheToolsList=True`, your OpenAI Agents SDK configuration handles high-volume user audits without hitting performance bottlenecks. It runs fast, keeps your user directory clean, and operates entirely within your specified security boundaries.

Custom table auditing via specialized agents

The `list_custom_table_rows` tool lets specialized OpenAI Agents SDK instances hand off work to one another. One agent can pull raw data from your custom tables, while a downstream agent analyzes the metrics and updates system objects. You build this by registering the MCP Server in your Python code using `MCPServerStreamableHttp`. The agents automatically discover tools like `get_single_object` and coordinate complex data-sync tasks on their own.

Setup guide

Set up Kentico (CMS & DXP) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Kentico (CMS & DXP) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Kentico (CMS & DXP) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kentico (CMS & DXP) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Kentico (CMS & DXP) Agent",
            instructions="You have access to Kentico (CMS & DXP) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint, then pass the server instance inside the `mcp_servers` list when instantiating your Agent.

Yes. You configure this by filtering the tools exposed through the Vinkius gateway or by defining system instructions that restrict the agent from calling write operations like `delete_system_object`.

Set `cacheToolsList=True` in your connection parameters. This prevents the agent from making redundant schema discovery requests every time it needs to call `get_site_document` or list users.

Absolutely. You can define one agent dedicated to reading tables using `list_custom_table_rows` and another that handles write operations like `create_system_object`, passing context between them using native SDK handoffs.

The data passes through Vinkius's secure, ephemeral V8 sandboxes directly to your OpenAI runtime. No personal data, user records retrieved via `get_user`, or document contents from `get_site_document` are stored on our servers.

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