How to Use the AudD Music Recognition MCP in Google ADK

Q: How do I connect Google ADK to the AudD Music Recognition MCP server?

You'll use the McpToolset from the Google ADK library. Initialize it with StreamableHttpServerParameters pointing to your Vinkius URL, then pass the toolset to your LlmAgent. The agent will then have access to all the AudD tools.

Q: Can a Gemini agent use AudD Music Recognition with Google ADK to find songs from a text query?

Yes. The searchmusic tool lets your agent find song metadata by sending a simple text query, like an artist and title. For lyric-based searches, the searchlyrics tool is the better choice.

Connect Gemini agents to AudD Music Recognition with Google ADK and index your media archives in BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AudD Music Recognition MCP to Google ADK

Create your Vinkius account to connect AudD Music Recognition 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 AudD Music Recognition with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Catalog Cloud Storage Audio

The `recognize_music` tool is your agent's entry point for identifying music. Point it at an audio file URL—maybe from Google Cloud Storage—and it returns clean metadata like artist, title, album, and streaming links. Because you're using Google ADK, your Gemini agent can process huge lists of files, call this tool for each one, and write the results straight into a BigQuery table. It’s a direct path from raw audio to a structured, searchable music database. Use `recognize_at_time` to target a specific section in large files.

Build Lyric-Aware Gemini Agents

Go beyond simple recognition. The `search_lyrics` tool lets your agent find songs based on a text snippet. This is perfect for building a conversational agent that can answer 'what's that song that goes...'. Once a song is identified, `get_lyrics` fetches the complete lyrics. You can use Gemini's long context to analyze lyrical themes across thousands of songs, all powered by this MCP Server and the data it provides.

React to Live Audio Streams on GCP

The AudD server can monitor live audio streams for you. Use the `add_monitored_stream` tool to tell it which stream to watch. It's designed for continuous sources like internet radio or live event feeds. Set a webhook with `set_stream_callback_url`, and your agent gets notified whenever a new song is detected. This MCP connection fits right into event-driven architectures on Google Cloud, letting you trigger Cloud Functions or other workflows when music is identified.

Setup guide

Set up AudD Music Recognition 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 AudD Music Recognition 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="AudD Music Recognition_agent",
    model="gemini-2.0-flash",
    instruction="You have access to AudD Music Recognition 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 AudD. 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 AudD Music Recognition 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 AudD Music Recognition MCP in Google ADK

You'll use the `McpToolset` from the Google ADK library. Initialize it with `StreamableHttpServerParameters` pointing to your Vinkius URL, then pass the toolset to your `LlmAgent`. The agent will then have access to all the AudD tools.

Yes. The `search_music` tool lets your agent find song metadata by sending a simple text query, like an artist and title. For lyric-based searches, the `search_lyrics` tool is the better choice.

Have your agent get a list of file URLs from Google Cloud Storage. Then, it can loop through them, calling the `recognize_music` tool on each one and writing the structured output directly to a BigQuery table. This MCP server is built for that kind of batch workload.

The tools take a URL, and AudD's service handles the audio processing on their end. As long as the URL points to a common audio or video format, it should work. You don't have to worry about transcoding.

Yes. Your agent only sends audio URLs and text fragments for lyric searches. Vinkius's zero-trust platform ensures the server runs in a completely isolated, ephemeral instance for your requests. Your GCP environment and data remain separate and secure.

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