AudD Music Recognition MCP for AI. Identify Songs, Lyrics, and Metadata from Audio.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
AudD Music Recognition connects your AI agent to a professional audio fingerprinting platform. It identifies songs by analyzing URLs, searching lyrics fragments, and pulling detailed track metadata (artist, album, release date).
You can monitor live audio streams for background music or search large files starting at specific timecodes. It also finds direct streaming links for identified tracks on Spotify and Apple Music.
What your AI can do
Add monitored stream
Sets up an audio source that the agent will continuously monitor for music identification.
Get lyrics
Pulls the complete, matched lyrics when given a specific song identifier or track name.
List monitored streams
Shows all audio streams that are currently set up for monitoring by the agent.
Pass any publicly accessible audio link to figure out what song it is.
Watch an ongoing audio feed or pinpoint a specific time in a long file to identify the music playing.
Input a few lines of lyrics and find the song and full text associated with them.
Retrieve metadata like the artist, album title, release date, and record label for any identified track.
Generate direct URLs so you can listen to the identified song on Spotify or Apple Music.
Ask an AI about this
Waiting for input…
AudD Music Recognition: 8 Available Tools
These eight tools cover every angle of audio analysis, letting you monitor streams, find metadata, and search lyrics from any source.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using AudD Music Recognition on VinkiusAdd Monitored Stream
Sets up an audio source that the agent will continuously monitor for music identification.
Get Lyrics
Pulls the complete, matched lyrics when given a specific song identifier or track...
List Monitored Streams
Shows all audio streams that are currently set up for monitoring by the agent.
Recognize At Time
Starts music identification on a long file, but only beginning at a specific second...
Recognize Music
Identifies a song by processing an audio URL and returns the artist, title, album...
Search Lyrics
Finds songs and associated metadata when you provide just a short text fragment of lyrics.
Search Music
Performs a general search for song titles or artists using plain text queries.
Set Stream Callback Url
Defines the webhook URL where results should be sent after continuous stream...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with AudD Music Recognition, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Tracking Down Background Music Details Is a Pain Point.
Right now, if you find an awesome track in a video, your workflow breaks. You have to pause the video, copy the URL, open Shazam, check Wikipedia for metadata, then manually paste it all into your notes. It's clicking through three different tabs and juggling five browser windows just to get basic credits.
With this MCP, that sequence of actions vanishes. Your agent handles the entire data pipeline in one prompt. You give it the link; it figures out the song identity, pulls the artist details, and even finds where you can stream it—all before you finish your thought.
Get Song Details with AudD Music Recognition MCP
You don't have to manually check streaming platforms for every song. The `recognize_music` tool finds the track and simultaneously returns multiple direct URLs, saving you the whole process of copy-pasting links into different services.
It’s about making that knowledge instantly available. Instead of treating music data like a series of disconnected manual lookups, it becomes one simple, reliable output from your agent.
What your AI can actually do with this
Think about this: you find a clip online, but the song playing underneath is never credited. Or maybe you remember only a few lines of lyrics from an old commercial—where did it come from? This MCP solves that. It lets your agent act like a dedicated musicologist. You feed it audio links or even just text fragments, and it does the heavy lifting.
It goes past simple Shazam-style identification; it pulls comprehensive data, including album details and direct streaming URLs for major platforms. Whether you're editing a video or doing deep research, this tool gives your agent the ability to analyze sound sources and retrieve precise information about music tracks using only natural conversation.
Because Vinkius hosts thousands of MCPs, integrating AudD means giving your AI client an entire professional library of audio data analysis tools right out of the box.
019d8418-fb02-72a6-821c-cee96f5d9130 Here's how it actually works
The bottom line is that your AI client handles all the complexity of audio fingerprinting and data retrieval behind one simple chat interface.
Subscribe to this MCP and provide your unique AudD API Token.
Connect your AI client, then prompt it with an audio URL or lyric snippet. You don't need to know the underlying tools; just ask the question.
Your agent uses its built-in logic to call the necessary functions, returning structured data like artist name, album info, and multiple streaming links.
Who is this actually for?
Content creators who need background music details for videos, researchers studying media history, or developers building applications that analyze sound streams.
Needs to identify the exact song playing in a video clip they found online, and needs both metadata (for credits) and streaming links (to license it).
Must analyze long audio files or live streams to detect specific musical events at precise timecodes for mastering or forensic analysis.
Requires analyzing music metadata across large datasets, pulling release dates and record label information to build a comprehensive database of cultural artifacts.
What Changes When You Connect
Stop manually cross-referencing song details. Use the recognize_music tool to analyze an audio URL in one step, getting the artist name, album info, and multiple streaming links immediately.
Don't struggle with background music in videos. Set up continuous monitoring using add_monitored_stream so your agent alerts you when a specific track is detected.
If you only remember a few lines of lyrics, use search_lyrics. It finds the full text and metadata without needing the original audio file—a huge time saver for researchers.
Need to analyze an hour-long podcast but only care about the segment at minute 45? Use recognize_at_time to pinpoint music recognition starting exactly at a specific offset.
When you need to integrate this into your own code, the MCP provides specialized tools like set_stream_callback_url, letting results flow automatically to another system or script.
See it in action
Podcast Editing
A producer finds a great background track from a YouTube video but needs the official album details for credits. The agent uses recognize_music on the URL, quickly pulling the artist and release date to complete the show notes.
Forensic Audio Analysis
An audio engineer is reviewing a long recording and needs to know what song played exactly 3:12 into the file. They use recognize_at_time to pinpoint the moment, getting immediate identification without manual scrubbing.
Academic Thesis Writing
A music researcher only has a snippet of lyrics from an old song and needs its full context. The agent uses search_lyrics, pulling the complete text and associated metadata for inclusion in their paper.
The honest tradeoffs
Searching by vague terms
Just asking the agent: 'Tell me about that song I heard last week.' The agent has no source material and can't give an answer.
Always provide a starting point. Use recognize_music with the audio URL, or if you only have text, use search_lyrics. Never rely on vague memory prompts.
Treating it like simple search
Trying to use basic chat commands to find a song's album details. The agent can’t pull structured data this way.
You must use the dedicated tools. For detailed info, use recognize_music first, and then follow up with requests for specific metadata.
Ignoring live streams
Forgetting that music detection requires continuous monitoring when analyzing a stream.
When dealing with ongoing audio, you need to add_monitored_stream first. This tells the MCP where and how often to listen for changes.
When It Fits, When It Doesn't
Use this MCP if your core problem is identifying music from sound—whether that sound is a live stream, an audio file URL, or just a few lines of text. It's perfect when you need concrete data points like streaming links or release dates. Don't use it if you already have the song title and artist name; then search_music is overkill. Similarly, don't rely on this for general file conversion or transcript generation; that requires a different type of tool altogether.
Questions you might have
How do I use `recognize_music` to find out what song is playing in an MP3 file? +
You simply pass the direct URL of the MP3 file into your agent. The recognize_music tool handles the fingerprinting and returns the artist, title, album data, and streaming links.
If I only have lyrics, how do I find the song? Do I need to use `search_lyrics`? +
Yes, that's exactly what search_lyrics is for. You just input a few lines of text, and it searches its database to match you with the correct track metadata.
Can I use `recognize_at_time` if the audio file is very long? +
Absolutely. This tool lets you specify an exact time offset (like 1:32) in a long audio file, so your agent only analyzes the music starting from that moment.
How does `add_monitored_stream` work for live radio? +
You use add_monitored_stream to set up a continuous feed. The MCP then monitors that stream and reports the song details when it detects a change in music.
When I use `set_stream_callback_url`, how does my agent receive music recognition results in real time? +
The webhook URL you provide receives the music data instantly. Your agent processes streaming events directly, eliminating the need for constant polling and making live monitoring efficient.
If I only have a vague phrase, how do I use `search_music` to find potential song metadata? +
It searches the database using text queries, returning title, artist, and album details. This works when you don't have a direct URL or enough lyrics for a precise match.
How do I check which audio streams are currently active using `list_monitored_streams`? +
It returns a list of all URLs and associated metadata you've set up for monitoring. This lets you verify your current monitoring scope before running new recognition jobs.
If I run `recognize_music` on an audio file with background noise, what kind of result do I get? +
The tool still attempts to pull core metadata despite noise. Results will provide the best match and often include a confidence score alongside the identified track details.
Can I identify a song just by providing a link to an MP3 file? +
Yes! Use the recognize_music tool and provide the direct URL to the audio file. Your agent will identify the track and provide metadata and streaming links.
How do I find the lyrics for a song if I only know a few words? +
You can use the search_lyrics tool with those words. Your agent will search AudD's database for matching lyrics and return the full text and song details.
Can I get direct links to open the song on Spotify or Apple Music? +
Yes, when identifying a song or searching for one, you can request extra data that includes direct streaming links for various platforms.
We've already built the connector for AudD Music Recognition. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.