How to Use the BannerBite MCP in Google ADK

Q: How do I initialize BannerBite with Google ADK?

Wrap your Vinkius URL in StreamableHttpServerParameters and pass it to McpToolset. Then hand that toolset to your LlmAgent under the tools parameter.

Q: Can Google ADK filter which BannerBite tools the agent sees?

You pass an array of strings to the toolnames argument. Restricting the agent to just generateimage and getrender keeps it focused strictly on static asset creation.

Q: How do I verify my BannerBite credentials through Google ADK?

Your agent runs getaccountcheck to test the underlying API connection. Doing this at initialization prevents failed render jobs later in the pipeline.

Q: Does the agent need to know the BannerBite project ID?

Yes, it calls getproject to fetch the specific details for a template. It needs those details to format the payload correctly for the rendering engine.

Connect BannerBite to Google ADK to generate videos and images directly from your BigQuery data using Gemini agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BannerBite MCP to Google ADK

Create your Vinkius account to connect BannerBite 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 BannerBite with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Batch render videos via Google ADK

Feeding a massive BigQuery dataset into a video generation pipeline requires an agent that can handle the context. Gemini reads your marketing data and pushes the variables into `generate_video` for thousands of personalized clips. You restrict the exposed functions using the `tool_names` filter in your `McpToolset` configuration. This forces the agent to only focus on rendering tasks, preventing it from accidentally calling `list_projects` when it should be generating media.

Map template bites with this MCP Server

Complex video templates contain multiple scenes that require specific text and image inputs. Your agent calls `list_bites` to map out the exact structure of a project before attempting to render it. Pushing this schema into Gemini's massive token window gives the model complete awareness of your entire template library. It reads the scene requirements and maps your Vertex AI data directly into the correct `generate_media` parameters.

Track generation queues

Asynchronous media generation means your agent needs a way to check on its work. Calling `list_renders` pulls the recent queue history to see which videos finished and which ones failed. If a specific job hangs, the agent targets it with `get_render` for detailed error logs. You build the logic to retry the generation or flag the specific BigQuery row for human review.

Setup guide

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

Wrap your Vinkius URL in `StreamableHttpServerParameters` and pass it to `McpToolset`. Then hand that toolset to your `LlmAgent` under the tools parameter.

You pass an array of strings to the `tool_names` argument. Restricting the agent to just `generate_image` and `get_render` keeps it focused strictly on static asset creation.

Your agent runs `get_account_check` to test the underlying API connection. Doing this at initialization prevents failed render jobs later in the pipeline.

Yes, it calls `get_project` to fetch the specific details for a template. It needs those details to format the payload correctly for the rendering engine.

Your BigQuery marketing strings and image assets pass through an ephemeral, zero-trust tunnel. Vinkius strips the authentication layer and terminates the runtime the millisecond the render request completes.

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