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

Q: How do I configure Kentico (CMS & DXP) with Google ADK?

Run pip install google-adk and define your toolset using McpToolset with your Vinkius HTTP URL. Pass this toolset into your LlmAgent constructor to make the MCP tools available to Gemini.

Q: Can I use Gemini's long context window to process Kentico (CMS & DXP) pages in Google ADK?

Yes. You can feed multiple document payloads fetched via getsitedocument directly into Gemini's context, allowing the model to perform bulk analysis of your site structure.

Q: How do I block destructive actions when using Kentico (CMS & DXP) with Google ADK?

Use the toolnames parameter when initializing your McpToolset. Omit tools like deletesystemobject or updatesystemobject to restrict the agent to read-only actions.

Q: How is my Kentico database data protected during Vertex AI runs?

Your CMS data, including custom table rows fetched via listcustomtablerows, flows directly through secure Google Cloud channels. Vinkius executes these requests in isolated, ephemeral sandboxes that never persist your database records.

Connect your Kentico CMS data to Gemini long-context models using Google ADK to analyze entire content trees at once.

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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze deep content structures using Google ADK

The `get_site_document` tool lets your Google ADK agent pull entire page trees and ingest massive amounts of CMS data. This MCP Server lets your agent pull entire page trees and analyze your content strategy in a single run. You register the toolset using `McpToolset` in your Python code. The agent then reads Kentico content, compares it with your enterprise datasets, and suggests updates without running out of memory.

Sync BigQuery data with Kentico tables

The `list_custom_table_rows` tool lets you bring your Google Cloud warehouse data directly into your Kentico tables using this MCP integration. Your agent can query BigQuery, process the metrics, and write them back to your custom tables using `update_system_object`. This bridges the gap between your cloud data stack and your Kentico platform. The Google ADK agent handles the translation, updating system records safely without manual data entry.

Restrict write operations for cloud security

The `delete_system_object` tool can be blocked using the `tool_names` filter to expose only read-only MCP tools like `get_single_object` and `list_users`. This ensures your agent can audit Kentico user directories or read system configurations without any risk of executing structural changes by mistake on Google Cloud.

Setup guide

Set up Kentico (CMS & DXP) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Kentico (CMS & DXP) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Kentico (CMS & DXP)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Kentico (CMS & DXP) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Run `pip install google-adk` and define your toolset using `McpToolset` with your Vinkius HTTP URL. Pass this toolset into your `LlmAgent` constructor to make the MCP tools available to Gemini.

Yes. You can feed multiple document payloads fetched via `get_site_document` directly into Gemini's context, allowing the model to perform bulk analysis of your site structure.

Use the `tool_names` parameter when initializing your `McpToolset`. Omit tools like `delete_system_object` or `update_system_object` to restrict the agent to read-only actions.

Yes. The Google ADK supports both transport methods, allowing you to connect to the managed MCP Server via secure HTTP streams or run it locally during development.

Your CMS data, including custom table rows fetched via `list_custom_table_rows`, flows directly through secure Google Cloud channels. Vinkius executes these requests in isolated, ephemeral sandboxes that never persist your database records.

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