How to Use the Deepgram MCP in Google ADK

Q: How do I pass Deepgram tools to a Google ADK agent?

You initialize the toolset using the McpToolset class with your HTTP server parameters. Pass this toolset instance directly into the LlmAgent constructor to expose the speech tools to Gemini.

Run Deepgram audio transcription and voice synthesis inside the Google ADK ecosystem using this managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deepgram MCP to Google ADK

Create your Vinkius account to connect Deepgram 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 Deepgram with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Audio Analysis in Google ADK

Feed hours of transcribed calls directly into Gemini's massive context window. This MCP Server allows your Google ADK agent to call `transcribe_audio_url` and push the resulting text straight into BigQuery for enterprise-grade sentiment analysis. Because Gemini handles huge token counts, you can transcribe multiple long audio files back-to-back and let the model find connections across days of recordings without hitches.

Dynamic Voice Generation from BigQuery Data

Pull customer records from your Google Cloud database and convert them into spoken alerts. The agent reads the database, processes the text, and triggers `convert_text_to_speech` to output natural audio files. This MCP setup handles the raw text conversion in the background, making voice synthesis a native capability of your cloud-hosted agent.

Cloud Resource and Model Auditing

Monitor your speech-to-text infrastructure directly from your terminal. Your agent can query `get_project_usage` and `list_deepgram_projects` to map active audio pipelines against your Google Cloud billing periods. By using the optional tool names filter, you can restrict your Gemini agent to only see `list_available_models`. This prevents the model from accessing administrative functions like api key listings while keeping speech tasks active.

Setup guide

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

You initialize the toolset using the `McpToolset` class with your HTTP server parameters. Pass this toolset instance directly into the `LlmAgent` constructor to expose the speech tools to Gemini.

Absolutely, you can write an agent that grabs transcripts via `transcribe_audio_url` and joins that text with structured customer data in BigQuery. The long-context window makes it easy to process both datasets simultaneously.

Use the optional tool names filter when setting up your MCP toolset. This lets you whitelist specific tools like `convert_text_to_speech` while blocking administrative tools like key listings.

Yes, the integration supports both transport layers. For production enterprise agents on Google Cloud, using the HTTP transport is generally preferred for scaling.

All audio URLs and transcripts are processed in-memory within zero-trust MCP sandboxes. Your voice data is never written to disk or used for training, ensuring strict compliance with enterprise data policies on Google Cloud.

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