SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Deepgram MCP with Google ADK

Connect Google ADK to Deepgram MCP. Transcribe meeting audio from this url, summarize podcast episode for quick review, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Deepgram logoDeepgram
Api Key

Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features.

17 Tools

Introduction

This guide walks you through connecting Deepgram to Google ADK using the Composio tool router. By the end, you'll have a working Deepgram agent that can transcribe audio, convert text to speech, browse available models, and track project usage and billing through natural language commands.

This guide will help you understand how to give your Google ADK agent real control over a Deepgram account through Composio's Deepgram MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Deepgram with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get a Deepgram account set up and connected to Composio
  • Install the Google ADK and Composio packages
  • Create a Composio Tool Router session for Deepgram
  • Build an agent that connects to Deepgram through MCP
  • Interact with Deepgram using natural language

What is Google ADK?

Google ADK (Agents Development Kit) is Google's framework for building AI agents powered by Gemini models. It provides tools for creating agents that can use external services through the Model Context Protocol.

Key features include:

  • Gemini Integration: Native support for Google's Gemini models
  • MCP Toolset: Built-in support for Model Context Protocol tools
  • Streamable HTTP: Connect to external services through streamable HTTP
  • CLI and Web UI: Run agents via command line or web interface

What is the Deepgram MCP server, and what's possible with it?

The Deepgram MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Deepgram account. It provides structured and secure access to Deepgram's speech AI services, so your agent can transcribe audio, generate summaries, convert text to speech, detect topics, and analyze project usage on your behalf.

  • Automated audio transcription: Your agent can transcribe pre-recorded audio files into accurate, readable text for effortless documentation and analysis.
  • Audio summarization: Have your agent generate quick, concise summaries of audio content, making it easy to review lengthy recordings in seconds.
  • Natural-sounding text-to-speech: Let your agent convert written text into lifelike speech audio using Deepgram's public TTS models for accessibility or creative applications.
  • Topic detection from audio: Enable your agent to identify and report on the main topics discussed within audio files, streamlining content review and categorization.
  • Usage analytics and project insights: Retrieve and analyze project usage metrics, scope permissions, and available models to optimize your Deepgram integration and monitor account health.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • A Google API key for Gemini models
  • A Composio account and API key
  • Python 3.9 or later installed
  • Basic familiarity with Python
2

Getting API Keys for Google and Composio

Google API Key
  • Go to Google AI Studio and create an API key.
  • Copy the key and keep it safe. You will put this in GOOGLE_API_KEY.
Composio API Key and User ID
  • Log in to the Composio dashboard.
  • Go to Settings → API Keys and copy your Composio API key. Use this for COMPOSIO_API_KEY.
  • Decide on a stable user identifier to scope sessions, often your email or a user ID. Use this for COMPOSIO_USER_ID.
3

Install dependencies

bash
pip install google-adk composio python-dotenv

Inside your virtual environment, install the required packages.

What's happening:

  • google-adk is Google's Agents Development Kit
  • composio connects your agent to Deepgram via MCP
  • python-dotenv loads environment variables
4

Set up ADK project

bash
adk create my_agent

Set up a new Google ADK project.

What's happening:

  • This creates an agent folder with a root agent file and .env file
5

Set environment variables

bash
GOOGLE_API_KEY=your-google-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id-or-email

Save all your credentials in the .env file.

What's happening:

  • GOOGLE_API_KEY authenticates with Google's Gemini models
  • COMPOSIO_API_KEY authenticates with Composio
  • COMPOSIO_USER_ID identifies the user for session management
6

Import modules and validate environment

python
import os
import warnings

from composio import Composio
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()

warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")
What's happening:
  • os reads environment variables
  • Composio is the main Composio SDK client
  • GoogleProvider declares that you are using Google ADK as the agent runtime
  • Agent is the Google ADK LLM agent class
  • McpToolset lets the ADK agent call MCP tools over HTTP
7

Create Composio client and Tool Router session

python
composio_client = Composio(api_key=COMPOSIO_API_KEY)

composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["deepgram"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url,
print(f"Composio MCP URL: {COMPOSIO_MCP_URL}")
What's happening:
  • Authenticates to Composio with your API key
  • Declares Google ADK as the provider
  • Spins up a short-lived MCP endpoint for your user and selected toolkit
  • Stores the MCP HTTP URL for the ADK MCP integration
8

Set up the McpToolset and create the Agent

python
composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": COMPOSIO_API_KEY}
    )
)

root_agent = Agent(
    model="gemini-2.5-flash",
    name="composio_agent",
    description="An agent that uses Composio tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Deepgram operations."
    ),
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")
What's happening:
  • Connects the ADK agent to the Composio MCP endpoint through McpToolset
  • Uses Gemini as the model powering the agent
  • Lists exact tool names in instruction to reduce misnamed tool calls
9

Run the agent

bash
# Run in CLI mode
adk run my_agent

# Or run in web UI mode
adk web

Execute the agent from the project root. The web command opens a web portal where you can chat with the agent.

What's happening:

  • adk run runs the agent in CLI mode
  • adk web . opens a web UI for interactive testing

Complete Code

Here's the complete code to get you started with Deepgram and Google ADK:

python
import os
import warnings

from composio import Composio
from composio_google import GoogleProvider
from dotenv import load_dotenv
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset

load_dotenv()
warnings.filterwarnings("ignore", message=".*BaseAuthenticatedTool.*")

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not GOOGLE_API_KEY:
    raise ValueError("GOOGLE_API_KEY is not set in the environment.")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment.")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment.")

composio_client = Composio(api_key=COMPOSIO_API_KEY, provider=GoogleProvider())

composio_session = composio_client.create(
    user_id=COMPOSIO_USER_ID,
    toolkits=["deepgram"],
)

COMPOSIO_MCP_URL = composio_session.mcp.url


composio_toolset = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url=COMPOSIO_MCP_URL,
        headers={"x-api-key": COMPOSIO_API_KEY}
    )
)

root_agent = Agent(
    model="gemini-2.5-flash",
    name="composio_agent",
    description="An agent that uses Composio tools to perform actions.",
    instruction=(
        "You are a helpful assistant connected to Composio. "
        "You have the following tools available: "
        "COMPOSIO_SEARCH_TOOLS, COMPOSIO_MULTI_EXECUTE_TOOL, "
        "COMPOSIO_MANAGE_CONNECTIONS, COMPOSIO_REMOTE_BASH_TOOL, COMPOSIO_REMOTE_WORKBENCH. "
        "Use these tools to help users with Deepgram operations."
    ),  
    tools=[composio_toolset],
)

print("\nAgent setup complete. You can now run this agent directly ;)")

Conclusion

You've successfully integrated Deepgram with the Google ADK through Composio's MCP Tool Router. Your agent can now interact with Deepgram using natural language commands.

Key takeaways:

  • The Tool Router approach dynamically routes requests to the appropriate Deepgram tools
  • Environment variables keep your credentials secure and separate from code
  • Clear agent instructions reduce tool calling errors
  • The ADK web UI provides an interactive interface for testing and development

You can extend this setup by adding more toolkits to the toolkits array in your session configuration.

TOOLS

Supported Tools

Every Deepgram action and event your agent gets out of the box.

Get Model by ID

Retrieve metadata for a specific Deepgram model by its UUID.

Get Public Models

Retrieve metadata on all public Deepgram models (speech-to-text and text-to-speech).

Get Project Balance

Retrieve one balance for a Deepgram project in its native units.

Get Project Billing Breakdown

Get a project's billing breakdown for an optional date range, preserving provider-reported amounts and units.

Get Project Request

Retrieve one request log for a Deepgram project by ID.

List Deepgram Projects

List Deepgram projects accessible to the API key.

Get Project Usage Breakdown

Get project usage grouped by provider usage fields, preserving native units.

Get Project Usage Summary

Retrieve aggregated project usage statistics, including speech durations, requests, channels, confidence and relevance, with usage breakdowns by model, accessor and tag.

List Project Balances

List all balances for a Deepgram project without converting their native amounts or units.

List Project Billing Fields

Return the fields available for project billing breakdowns.

List Project Purchases

List purchases for a Deepgram project without converting native values.

List Project Requests

List request logs for a Deepgram project with date and page controls.

List Project Scopes

Return a static list of Deepgram permission scope types and their descriptions.

List Project Usage Fields

Return the fields available for project usage breakdowns.

List Think Models

Tool to list available think models for AI agent processing and voice agent configuration.

Transcribe Pre-recorded Audio

Transcribe pre-recorded audio from a publicly accessible URL, returning the primary transcript in the first channel and alternative.

Text-to-Speech (REST)

Convert text to speech and return base64-encoded audio with its content type.

FRAMEWORKS

How to build Deepgram MCP Agent with another framework

Claude Code logo

Claude Code

Use Deepgram MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Deepgram MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Deepgram MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Deepgram MCP with Claude Agent SDK

Codex logo

Codex

Use Deepgram MCP with Codex

OpenClaw logo

OpenClaw

Use Deepgram MCP with OpenClaw

Hermes logo

Hermes

Use Deepgram MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Deepgram MCP with Atomic Agent

LangChain logo

LangChain

Use Deepgram MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Deepgram MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Deepgram MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Deepgram MCP with LlamaIndex

CrewAI logo

CrewAI

Use Deepgram MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Deepgram MCP with Pydantic AI

AutoGen logo

AutoGen

Use Deepgram MCP with AutoGen

FAQ

Frequently asked questions

Start with Deepgram.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Deepgram tool your agent needs.Free to start.

Start building