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

Q: How do I initialize AutoGen with Kentico (CMS & DXP)?

Use mcpservertools with a StreamableHttpServerParams configuration pointing to Vinkius. Pass the resulting tool list to your AssistantAgent.

Q: How do multiple AutoGen agents share Kentico (CMS & DXP) user data?

The first agent calls getuser and the resulting JSON enters the shared conversation context. Every other agent in the chat reads that exact same data.

Q: Do I need custom code to map Kentico tools to my agents?

No. The McpToolAdapter automatically converts the tools into the exact schema your agents expect.

Deploy debating AutoGen agents to audit, negotiate, and update your Kentico (CMS & DXP) configuration via MCP.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

System Configuration Debates

The `create_system_object` and `delete_system_object` tools allow agents to modify the core Kentico architecture. In AutoGen, you assign one agent to propose a deletion and another to evaluate the risk. The security agent reviews the dependencies before allowing the execution. If the proposal fails the safety check, the agents negotiate an alternative, like updating the object instead of removing it.

AutoGen MCP Server Audits

You use the `list_users` tool to feed account data into a multi-agent review panel. An HR agent checks employment status while an IT agent verifies the Kentico permissions via the MCP Server. When they spot a discrepancy, they trigger `get_user` for deeper inspection. The agents discuss the findings and output a final consensus report on which accounts need termination.

Content Review Workflows

The `get_site_document` tool pulls a draft page into the conversation. A copywriter agent suggests edits for clarity, while an SEO agent argues for specific keyword inclusions. They iterate on the text until both agents agree on the final version. Once consensus is reached, the execution agent calls `update_site_document` to push the negotiated content back to the CMS.

Setup guide

Set up Kentico (CMS & DXP) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Kentico (CMS & DXP) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Kentico (CMS & DXP)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kentico (CMS & DXP) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Kentico (CMS & DXP)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kentico (CMS & DXP) data")
    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 AutoGen

Use `mcp_server_tools` with a `StreamableHttpServerParams` configuration pointing to Vinkius. Pass the resulting tool list to your `AssistantAgent`.

You control the safety constraints. The agents debate the action, but you can require human-in-the-loop approval before `delete_system_object` actually fires.

The first agent calls `get_user` and the resulting JSON enters the shared conversation context. Every other agent in the chat reads that exact same data.

No. The `McpToolAdapter` automatically converts the tools into the exact schema your agents expect.

Vinkius handles the transport through an isolated, single-use sandbox. When `get_site_document` exposes your proprietary web copy to the agents, the connection is authenticated via a single endpoint token and leaves no trace on the host environment.

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