How to Use the Builder MCP in Google ADK

Q: Can I filter which Builder tools my Google ADK agent can see?

Yes, use the toolnames filter parameter in your StreamableHttpServerParameters config. You can limit a specific Google ADK instance to read-only tools like getsinglecontent and listmodelcontent.

Analyze and update massive Builder CMS models with Gemini long-context reasoning using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Builder MCP to Google ADK

Create your Vinkius account to connect Builder 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 Builder with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run deep audits on Builder schemas with Google ADK

`list_builder_models` pulls your entire CMS structure directly into the Gemini long-context window. Google ADK processes thousands of fields at once, letting you map your CMS layout against enterprise data warehouses. By combining this schema data with BigQuery analytics, your agent writes highly targeted updates back to your models. You no longer guess which models are active because the agent checks live data first.

Bulk content ingestion via Google ADK MCP Server

`create_visual_block` pushes new layout configurations directly from your Google Cloud data pipelines into Builder. Your Google ADK agent reads product catalogs from Cloud Storage and formats them into visual components. The agent handles high-volume generation by calling `list_model_content` to check for duplicates before writing. This keeps your production layout clean and prevents redundant blocks.

Real-time CMS inventory checks

`count_model_entities` gives your Google ADK agent an instant count of live entries in any model via this MCP tool. This tool lets your Gemini-powered agent monitor content drift across massive enterprise spaces without pulling heavy payloads. When counts mismatch your BigQuery inventory, the agent uses `update_visual_block` to sync the visual layouts. It operates autonomously within your Google Cloud security perimeter.

Setup guide

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

Install google-adk and configure McpToolset with your Vinkius HTTP URL. Pass this toolset into your LlmAgent constructor. This exposes the entire suite of Builder tools directly to your Gemini model.

Yes, use the tool_names filter parameter in your StreamableHttpServerParameters config. You can limit a specific Google ADK instance to read-only tools like get_single_content and list_model_content.

Your Google ADK agent can ingest every model schema returned by list_builder_models alongside thousands of content entries from list_model_content. This lets the model find structural inconsistencies across your entire CMS in a single run.

Yes, Google ADK connects to the Vinkius-hosted server over secure HTTP, but you can also run it locally via Stdio during development. Both setups expose the same tools like search_active_models and get_media_file.

Your credentials stay encrypted inside the Vinkius zero-trust sandbox. Your Google ADK agents only interact with the sandboxed MCP tools, ensuring your proprietary media files and model schemas are never exposed to public networks.

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