AudD Music Recognition MCP. Pinpoint any song from an audio file or lyric snippet.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
AudD Music Recognition MCP identifies songs from any audio source, whether it’s a URL, a video snippet, or just a few lines of lyrics.
It pulls detailed metadata—artist, album, release date—and finds direct streaming links for Spotify and Apple Music using your AI agent.
What your AI agents can do
Add monitored stream
Starts monitoring a continuous audio stream so the system can detect music playing in real-time.
Get lyrics
Get full lyrics for a specific track
List monitored streams
Returns a list of all audio streams that are currently being monitored by the agent.
Pass an audio file link and receive the artist, title, album data, and links for major streaming services.
Pinpoint a song playing within a longer audio recording by specifying the exact time offset.
Search for full lyrics or retrieve metadata when you only know a few lines of song text.
Monitor live or recorded streams by adding, listing, and setting callbacks for audio content detection.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
AudD Music Recognition: 7 Tools
Use these tools to detect music in streams, find song details from URLs, or search for lyrics and metadata across various media types.
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 Vinkius019d8418add monitored stream
Starts monitoring a continuous audio stream so the system can detect music playing in real-time.
019d8418get lyrics
Get full lyrics for a specific track
019d8418list monitored streams
Returns a list of all audio streams that are currently being monitored by the agent.
019d8418recognize at time
Determines what song is playing by analyzing an audio file starting at a specific time offset.
019d8418recognize music
Identifies a song from a given audio URL and returns the artist, title, album, and direct links to major music platforms.
019d8418search lyrics
Searches for full lyrics or retrieves metadata when you provide only a text fragment of a song.
019d8418search music
Performs a general database search to find song details based on a keyword query like an album name or genre.
019d8418set stream callback url
Configures the monitoring system by setting a webhook URL where results will be automatically sent upon detection.
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 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ 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 server provides 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Manually figuring out where an unknown song comes from is a nightmare.
Right now, if you hear music on a video and need to know who made it or find the track for licensing, you end up copy-pasting URLs into four different sites: Google Images, Shazam alternatives, YouTube's search bar, and then manually checking Spotify. It’s time-consuming click-through work.
With this MCP, your agent handles the whole pipeline in one go. You pass the audio source, and you get back a clean data object containing everything—the artist, title, album, and direct links to major streaming platforms. The task goes from half an hour of clicking down to one prompt.
You get full control over identifying unknown music using recognize_music.
Previously, if you were analyzing a long audio file for content, you could only confirm the song at the start or end. Finding a specific track in the middle meant stopping everything and manually checking timestamps against external services.
Now, using recognize_at_time lets your agent pinpoint that exact moment in the recording and give you the full metadata for that segment. The data is immediate and actionable.
What you can do with this MCP connector
This connector lets your agent act like an expert musicologist. You don't need to hop between Google Search, YouTube, and multiple streaming sites anymore. Just give the audio or a lyric fragment to your client, and it handles everything.
It can take a direct audio URL and instantly return all the track details: who wrote it, what album it came from, and where you can stream it. Need to pinpoint a song playing in a long video? It recognizes music even starting at a specific time marker. If you just remember a line of lyrics, it finds the full song information for you.
The real power comes when you combine this MCP with others. You can chain an agent's workflow: first using this recognition layer to identify a track, and then passing that artist name into a messaging MCP to alert your team about the find. Because every tool call runs within its own V8 isolate sandbox inside Vinkius, you get predictable execution and rock-solid security without having to worry about managing complex infrastructure.
019d8418-fb02-72a6-821c-cee96f5d9130 
How AudD Music Recognition MCP Works
- 1 Subscribe to this MCP in Vinkius and enter your AudD API Token.
- 2 Connect your preferred AI client (Claude, Cursor, etc.) to the catalog using that single connection.
- 3 Tell your agent what you want: 'Find the song at this URL' or 'Search for lyrics containing...'.
The bottom line is you get instant, actionable music data without manually jumping between specialized tools.
Who Is AudD Music Recognition MCP For?
Content creators, media researchers, and developers who spend time verifying background music sources or analyzing track origins. You're tired of cross-referencing five different websites just to confirm a song title.
Uses the MCP to identify unknown background tracks from video files, ensuring they have proper licensing or source metadata.
Pulls song details and historical album information by searching for lyrics fragments found in old recordings or archived media.
Integrates music identification capabilities into a larger agent workflow, using the stream monitoring tools to feed data into other systems.
What Changes When You Connect
- Get complete track details instantly. Instead of just getting a name, you get the artist, album, and streaming links for Spotify and Apple Music all in one go.
- Handle long-form media. If you're analyzing hours of recorded audio, use recognize_at_time to zero in on specific songs without manually scrubbing through the file.
- Manage live feeds automatically. Use add_monitored_stream and set_stream_callback_url to build systems that detect music activity and notify other tools when a track starts playing.
- Search by lyrics, not title. If you only remember 'I just wanna know how it feels,' search_lyrics finds the song even if you don't know the artist or album.
- Avoid manual lookups. Use search_music to get basic metadata on an unknown genre or era of music without needing a direct audio source.
Real-World Use Cases
Archiving old media footage
A documentary filmmaker needs to identify the background music in a 45-minute archival tape. They use recognize_at_time repeatedly across different sections, gathering enough metadata to catalog every piece of music played.
Verifying content credits
A digital asset manager needs to prove the source of a song snippet found online. They use recognize_music on the URL and then chain that data into a billing MCP to automatically generate usage reports.
Building real-time monitoring tools
An event security team wants to know if copyrighted music is being played in a public space. They use add_monitored_stream and set_stream_callback_url to build an automated alert system for their AI agent.
Investigating uncredited songs
A journalist finds a song with no credits attached. They first use search_music with vague keywords, then refine the results using search_lyrics based on overheard dialogue to nail down the source material.
The Tradeoffs
Searching for music metadata in general web searches
Copying a random audio URL and pasting it into Google. You get ads, redirects, and maybe nothing useful about the artist or streaming links.
→ Use recognize_music directly with your agent. It processes the URL internally to give you structured data for the artist, title, album, and direct streaming links.
Trying to find lyrics from a simple search engine query
Searching 'lyrics never gonna give you up' on Google results in dozens of forum posts. You have to click through several sites to get the full text.
→ Use search_lyrics. This tool directly queries its database and returns the matched lyrics along with accurate song metadata, saving you clicks.
Manually tracking multiple audio streams
If an agent needs to monitor background music in three different video feeds, the user has to remember to manually start monitoring each one.
→ Use add_monitored_stream for each feed. Then use list_monitored_streams to verify that all streams are running and active.
When It Fits, When It Doesn't
You need this MCP if your job involves identifying, cataloging, or tracking music when you don't have enough information—whether it’s just a URL, a partial lyric, or an unknown audio segment. Use recognize_music for general identification from files; use search_lyrics when the text is your only clue. However, don't use this if you already possess all the metadata (artist, album, etc.). In that case, you're better off using a dedicated data storage MCP to simply record and archive the known facts. Also, remember that if you want continuous monitoring, you must set up the callback URL first; otherwise, your stream detection won't pass results out of the system.
Common Questions About AudD Music Recognition MCP
How do I use AudD Music Recognition to find a song from a video URL? +
You pass the direct audio URL to the recognize_music tool. It handles the identification process, returning structured data with the artist, title, and streaming links.
Does AudD Music Recognition work for long files? +
Yes, you use the recognize_at_time tool to target specific sections of a file. You tell the agent which offset in the audio file needs checking.
Can I get lyrics using the search_lyrics tool? +
The search_lyrics tool finds full lyrics or matches text fragments against its database, giving you more than just a vague reference.
How do I monitor a continuous stream with AudD Music Recognition? +
Start by using add_monitored_stream to begin tracking the feed. You'll need set_stream_callback_url if you want the detection results automatically sent elsewhere.
How do I check which streams are currently being monitored using the list_monitored_streams tool? +
You call list_monitored_streams to pull a list of all active audio monitoring jobs. This shows you exactly what's running and if any streams need attention or removal.
What is the best way to use recognize_at_time for pinpoint accuracy in long audio files? +
You specify a precise offset time when calling recognize_at_time. This tells the system exactly where to start listening, skipping irrelevant beginning sections.
How do I configure webhooks for real-time results using set_stream_callback_url? +
You use set_stream_callback_url to provide a specific webhook endpoint. This ensures that when the stream monitoring is done, the result hits your server instantly.
Does the search_music command handle queries that aren't directly linked to an audio file? +
Yes, search_music lets you look up songs using just a text description. This is useful for finding metadata before you have an actual URL.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.