How to Use the Elemeno MCP in Google ADK

Q: How do I register the Elemeno MCP Server inside my Google ADK agent?

Install the library with pip install google-adk. Instantiate McpToolset(serverparams=StreamableHttpServerParameters(url="YOURVINKIUSENDPOINT")) and pass it to your LlmAgent in the tools array to expose the content tools to Gemini.

Q: Can I limit which Elemeno tools my Google ADK agent can access?

Yes. You can pass an optional toolnames filter to the McpToolset constructor. This restricts the exposed tools, ensuring your agent only sees specific operations like listpublishedcontent and cannot call account metadata tools.

Q: How does Gemini use Elemeno metadata for reasoning?

Gemini queries getelemenoaccountmetadata to check account limits and structures. It then uses this metadata to plan how to partition large content extraction jobs across multiple runs.

Connect Gemini models to your Elemeno CMS using Google ADK to analyze content structures alongside enterprise BigQuery datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elemeno MCP to Google ADK

Create your Vinkius account to connect Elemeno 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 Elemeno with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-million token content analysis with Google ADK

The `list_published_content` tool identifies all items currently in a published status within your Elemeno CMS. Because Gemini models handle over a million tokens of context, your agent can pull hundreds of articles at once without hitting context limits. This MCP Server allows your Gemini agent to cross-reference live marketing content with customer data stored in BigQuery. The agent reads the published list, pulls full text, and drafts performance reports directly in your Google Cloud environment.

Global settings and singleton tracking

The `list_content_singletons` tool retrieves all unique global pages and settings blocks from your Elemeno CMS. Your Google ADK agent uses this MCP tool to locate global configuration data, like site headers or localized footer text. Once found, the agent calls `get_singleton_content` to read the actual values. This lets your enterprise agent verify that global configurations match the deployment rules set in your Google Cloud infrastructure.

Deep collection auditing and catalog search

The `list_content_collections` tool pulls all configured collections from your Elemeno account. Your agent can then run `search_collection_content` to find specific entries matching your enterprise product catalogs. This setup allows your Google ADK agent to act as a real-time router. It checks your CMS structure, finds matching items, and prepares structured data payloads for downstream Vertex AI processing pipelines.

Setup guide

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

Install the library with `pip install google-adk`. Instantiate `McpToolset(server_params=StreamableHttpServerParameters(url="YOUR_VINKIUS_ENDPOINT"))` and pass it to your `LlmAgent` in the `tools` array to expose the content tools to Gemini.

Yes. You can pass an optional `tool_names` filter to the `McpToolset` constructor. This restricts the exposed tools, ensuring your agent only sees specific operations like `list_published_content` and cannot call account metadata tools.

The connection uses a secure, ephemeral V8 isolate on Vinkius that hosts the MCP Server and handles your Elemeno API token securely. Your content collections and singleton values are never used to train Gemini models and are discarded immediately after the tool execution completes.

Yes. The Google ADK toolset handles both standard I/O for local development and HTTP transport for deployed Google Cloud Run services, making it easy to query your Elemeno CMS via MCP from any environment.

Gemini queries `get_elemeno_account_metadata` to check account limits and structures. It then uses this metadata to plan how to partition large content extraction jobs across multiple runs.

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