How to Use the 3Scribe MCP in Google ADK

Q: How does my Google ADK agent start a 3Scribe transcription through its MCP connection?

The agent calls createjob with a media URL. The McpToolset you configured sends the request to the 3Scribe server, which returns a job ID for tracking.

Q: Can I use a Google ADK agent to get text from a 3Scribe job and save it to BigQuery?

Yes, that's a core use case. Your agent calls getjob to get the text, then you can have it use another tool to run an INSERT statement on a BigQuery table. It connects your media to your data warehouse.

Q: What's the best way to monitor multiple transcription jobs?

Have your agent call listjobs. This gives you a full overview of everything in your account. For real-time monitoring of one job, you can have the agent poll the getjob endpoint until the status changes to complete.

Connect your Google ADK agents to 3Scribe. Transcribe audio and video, then feed the text directly into your BigQuery tables or Vertex AI pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 3Scribe MCP to Google ADK

Create your Vinkius account to connect 3Scribe 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 3Scribe with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Audio into BigQuery-Ready Text

Your Gemini-powered agent can take a media URL and kick off a transcription job with `create_job`. 3Scribe processes the file and returns a job ID. Your agent then uses `get_job` to pull the finished text. Because you're using the Google ADK, you can pass that text right into a BigQuery insert or a Vertex AI model for further analysis. It’s a direct path from audio to your data warehouse.

Manage Transcription Jobs at Scale

If you're running many transcription tasks, your agent can use `list_jobs` to get a full history. This is useful for building dashboards or logging job activity in Google Cloud Logging. When it's time to clean up, the agent calls `delete_job` to permanently remove a transcription. This helps manage storage and keeps your 3Scribe account tidy. It's a simple operation that fits right into an automated data lifecycle on Google Cloud.

An MCP Toolset for Google ADK

Setting up this MCP Server is simple. After you install the `google-adk` package, you define an `McpToolset` using your Vinkius server URL. This toolset wraps all the 3Scribe operations. Just pass this toolset into your `LlmAgent`'s `tools` list. The Gemini model will automatically understand how to use `create_job` and the other functions. You can even use the `tool_names` filter to expose only specific tools to certain agents.

Setup guide

Set up 3Scribe 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 3Scribe 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="3Scribe_agent",
    model="gemini-2.0-flash",
    instruction="You have access to 3Scribe 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 3Scribe. 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 3Scribe 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 3Scribe MCP in Google ADK

The agent calls `create_job` with a media URL. The `McpToolset` you configured sends the request to the 3Scribe server, which returns a job ID for tracking.

Yes, that's a core use case. Your agent calls `get_job` to get the text, then you can have it use another tool to run an `INSERT` statement on a BigQuery table. It connects your media to your data warehouse.

Definitely. You can program your agent to periodically call `list_jobs`, check the dates, and then use `delete_job` to remove any transcriptions older than a certain age. It's great for automated data hygiene.

Have your agent call `list_jobs`. This gives you a full overview of everything in your account. For real-time monitoring of one job, you can have the agent poll the `get_job` endpoint until the status changes to complete.

The server processes the media URLs for transcription and the generated text. Your Vinkius token authenticates every request. The entire MCP server runs in a sandboxed environment, separate from other processes, keeping your job data isolated.

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