How to Use the Agility CMS MCP in Google ADK

Q: Can Google ADK filter which Agility CMS tools are exposed?

Yes. You can use the toolnames filter in the toolset configuration. This restricts the agent to only use safe operations like getsingleitem while hiding sync commands.

Q: How does Google ADK read the Agility CMS sitemap?

The agent calls getsitetree with a target channel name. This returns the nested architecture, which Gemini can easily parse thanks to its massive context window.

Q: Can I search Agility CMS content natively from Google Cloud?

You can. The searchcontentreference tool lets your agent query specific keywords inside a content reference list directly from your Google ADK setup.

Feed Agility CMS content into Google ADK. Let Gemini agents analyze entire sitemaps and sync articles into your Google Cloud workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agility CMS MCP to Google ADK

Create your Vinkius account to connect Agility CMS 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 Agility CMS with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Massive CMS Context to Google ADK

The `list_content_items` tool pulls bulk records from any Agility CMS reference list straight into your agent. Gemini models handle over a million tokens of context. You can dump thousands of blog posts or author bios directly into the context window. From there, your agent cross-references that data with BigQuery tables. Using `count_reference_items`, the agent knows exactly how large the list is before initiating the fetch.

Analyze Media and Layouts

The `get_media_gallery` tool retrieves specific gallery mappings containing photos. Visual and structural data require precise mapping. Your Gemini agent reads the exact media relationships tied to your content. To understand where those photos live, `get_page_layout` extracts the structural modules of a single page. This gives your Google Cloud enterprise agent the full blueprint of your digital channel.

Keep Vertex AI Synced via MCP Server

The `sync_incremental_pages` tool pulls only the routing updates since your last token. Enterprise systems cannot rely on stale data. Your agent tracks changes without overloading the CMS API. The same logic applies to content. Calling `sync_incremental_items` fetches the latest articles or product listings. You connect the Vinkius MCP endpoint to your toolset and start streaming updates into Vertex AI.

Setup guide

Set up Agility CMS 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 Agility CMS 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="Agility CMS_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Agility CMS 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 Agility CMS. 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 Agility CMS 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 Agility CMS MCP in Google ADK

Install google-adk and set up an McpToolset using StreamableHttpServerParameters. Point the URL to your Vinkius endpoint, then pass the toolset to your LlmAgent.

Yes. You can use the tool_names filter in the toolset configuration. This restricts the agent to only use safe operations like get_single_item while hiding sync commands.

The agent calls get_site_tree with a target channel name. This returns the nested architecture, which Gemini can easily parse thanks to its massive context window.

You can. The search_content_reference tool lets your agent query specific keywords inside a content reference list directly from your Google ADK setup.

The server processes media galleries, nested sitemaps, and content reference lists. Vinkius routes this traffic through an ephemeral, isolated sandbox that drops all memory the second the HTTP stream closes.

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