How to Use the AudD Music Recognition MCP in OpenAI Agents SDK

Q: How does my agent use AudD Music Recognition with the OpenAI Agents SDK?

Your agent auto-discovers the tools. Just instantiate the MCPServerStreamableHttp client with your Vinkius endpoint URL and pass it to your Agent's constructor. The tools like recognizemusic will be available immediately.

Q: Can I search for a song if I only know some lyrics using AudD Music Recognition and the OpenAI Agents SDK?

Yes, that's what the searchlyrics tool is for. Your agent can pass a text fragment to the tool, and it will return a list of matching songs and their metadata. It's a direct way to solve 'what's that song that goes...' questions.

Q: Can my OpenAI Agents SDK agent use AudD Music Recognition to find a song in a long audio file?

Absolutely. Instead of recognizemusic, your agent should use the recognizeattime tool. You provide the audio URL and a specific time offset in seconds, and this MCP server will identify the song playing at that exact moment.

Build production music bots with the OpenAI Agents SDK that identify songs, find lyrics, and monitor audio streams.

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 OpenAI Agents SDK

Create your Vinkius account to connect AudD Music Recognition to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Identify Music from Any URL

The `recognize_music` tool takes an audio URL and returns the song's artist, title, and album. It also gives you direct links to stream it on major platforms. Your agent can call this tool and the OpenAI SDK's built-in guardrails will validate the action before it even runs. This means you can build agents that reliably catalog audio files or respond to user queries about music, with full tracing available in your OpenAI dashboard. For long audio, `recognize_at_time` lets you jump to a specific timestamp so you're not processing the whole file.

Find Lyrics by Text or Track

Give your agent two ways to find song lyrics. The `search_lyrics` tool finds songs that match a line or phrase you provide. It's great for when you only know a few words and want your agent to figure out the rest. If you already have a track ID from another AudD tool, `get_lyrics` pulls the full, clean lyrics for that specific song. It's a direct way to add lyric features to your agent without messy web scraping. This MCP server gives your agent clean, structured data every time.

Monitor Live Streams with this MCP Server

This isn't just for static files. The `add_monitored_stream` tool lets your agent watch a live audio stream for any music that plays. You point it at an HLS or Icecast stream, and AudD does the rest. When a song is identified, the server sends the data to a webhook you define with `set_stream_callback_url`. This lets you build reactive systems, like a bot that posts 'Now Playing' updates for an internet radio station. You can check what's being watched with `list_monitored_streams`.

Setup guide

Set up AudD Music Recognition MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all AudD Music Recognition tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AudD Music Recognition tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AudD Music Recognition tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="AudD Music Recognition Agent",
            instructions="You have access to AudD Music Recognition tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent auto-discovers the tools. Just instantiate the `MCPServerStreamableHttp` client with your Vinkius endpoint URL and pass it to your Agent's constructor. The tools like `recognize_music` will be available immediately.

Yes, that's what the `search_lyrics` tool is for. Your agent can pass a text fragment to the tool, and it will return a list of matching songs and their metadata. It's a direct way to solve 'what's that song that goes...' questions.

It returns direct links to the song on major platforms. The data includes links for Spotify, Apple Music, Deezer, and others, so your agent can give users a way to listen right away.

Absolutely. Instead of `recognize_music`, your agent should use the `recognize_at_time` tool. You provide the audio URL and a specific time offset in seconds, and this MCP server will identify the song playing at that exact moment.

The server only processes the audio URLs or text fragments you send for recognition. Vinkius runs each MCP server in an ephemeral, zero-trust sandbox. Your data is used for the request and then discarded; nothing is logged or stored.

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