How to Use the Maestra MCP in Google ADK

Q: What's the setup for using Maestra with the Google ADK?

After pip install google-adk, you create an McpToolset. Point its serverparams to your Vinkius URL using StreamableHttpServerParameters and pass the toolset to your LlmAgent.

Q: Can I restrict which Maestra tools my Google ADK agent can access?

Yes, the McpToolset constructor accepts a toolnames filter. You can pass a list of strings, like 'getfiledetails', 'listmaestrafiles', to expose only specific tools to the agent.

Q: What about data privacy when connecting Google ADK to Maestra?

Your media files, passed via URL to uploadmediafortranscription, are the primary data processed. Vinkius isolates each request in a sandboxed environment, and all access is governed by your single endpoint token, never exposing your underlying Maestra keys.

Run large-scale media localization on Google Cloud by connecting the Google ADK to Maestra.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maestra MCP to Google ADK

Create your Vinkius account to connect Maestra 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 Maestra with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Transcription in Your GCP Project

This Maestra MCP Server plugs directly into your Google Cloud workflow. Your Gemini-powered agent can take a file URL—maybe from a Cloud Storage bucket—and submit it for processing with `upload_media_for_transcription`. The agent then polls the job status using `get_file_details`. Once transcription is complete, it can pull the results with `export_transcription_results` and write them straight to BigQuery for analysis.

Localize Content with Gemini's Context

Use Gemini's long-context window to reason about your localization strategy. The agent can use `list_maestra_files` to get an inventory, then decide which files need new language versions. From there, it calls `translate_transcription` for each target language and follows up with `generate_ai_voiceover` to create the final audio. It's a full localization pipeline managed by a single agent.

A Managed MCP Server for Google ADK

Forget about managing another service. This server is hosted by Vinkius, giving your Google ADK agent a single, secure endpoint for all Maestra operations. Your agent can manage its workspace by listing assets with `list_maestra_files` and `list_account_folders`, keeping your GCP-based workflow clean and organized without extra ops overhead.

Setup guide

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

After `pip install google-adk`, you create an `McpToolset`. Point its `server_params` to your Vinkius URL using `StreamableHttpServerParameters` and pass the toolset to your `LlmAgent`.

The agent first needs a transcribed file ID. It can then call `list_available_ai_voices` to see options and execute `generate_ai_voiceover` with the file ID and a selected voice ID.

Yes, the `McpToolset` constructor accepts a `tool_names` filter. You can pass a list of strings, like `['get_file_details', 'list_maestra_files']`, to expose only specific tools to the agent.

Indirectly. Your Google ADK agent can generate a publicly accessible URL for a file in GCS, then pass that URL to the `upload_media_for_transcription` tool.

Your media files, passed via URL to `upload_media_for_transcription`, are the primary data processed. Vinkius isolates each request in a sandboxed environment, and all access is governed by your single endpoint token, never exposing your underlying Maestra keys.

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