How to Use the AudD Music Recognition MCP in Windsurf

Q: Can Windsurf find a song if I only know a few words?

Yes. Cascade calls the searchlyrics endpoint with your text snippet. It returns the matched track details, which your agent can then use to fetch the full text or streaming links.

Let Windsurf identify songs, search lyrics, and monitor audio streams right inside your editor.

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 Windsurf

Create your Vinkius account to connect AudD Music Recognition to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audio Recognition in Windsurf

The `recognize_music` tool pulls artist, title, album, and streaming links straight from an audio URL. You pass a link to an MP3 or WAV file, and Cascade fetches the exact track details. It hands you links to major streaming platforms so you don't have to open a browser. Long files need precision. Cascade uses `recognize_at_time` to pinpoint tracks starting at a specific offset. Tell your agent to find the background song at the two-minute mark of a podcast, and it pulls the exact data. No more guessing timestamps.

Find Tracks by Lyrics

The `search_lyrics` tool matches text fragments against a global music database to find song metadata. You type a few remembered lines into your IDE, and Cascade queries the MCP Server to return the exact track. Sometimes you need the full text for a project. Calling `get_lyrics` grabs the complete song words for a specific track ID. Your agent pulls this text directly into your active workspace or markdown file.

Continuous Audio Monitoring

The `add_monitored_stream` tool tells the AudD Music Recognition service to watch a live audio feed. You provide a radio station or live event URL, and the system listens for recognized tracks in real time. Cascade manages the callbacks automatically. It triggers `set_stream_callback_url` to define where those identification events go, and runs `list_monitored_streams` to show you exactly which feeds are currently active.

Setup guide

Set up AudD Music Recognition MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the AudD Music Recognition MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my AudD Music Recognition payment history." If connected, Cascade will call the AudD Music Recognition tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "audd-music-recognition-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Open Settings, go to Cascade, and find the MCP Servers UI. You can search the built-in marketplace for a one-click install or edit your `~/.codeium/windsurf/mcp_config.json` file directly. Click refresh, and Cascade will discover the new audio tools.

Yes. Cascade calls the `search_lyrics` endpoint with your text snippet. It returns the matched track details, which your agent can then use to fetch the full text or streaming links.

The server processes standard audio URLs pointing to formats like MP3 or WAV. You feed the direct link to the agent, and it handles the API request to identify the track.

It handles continuous feeds. You point the server at a live broadcast URL, and it monitors the audio, sending track data to your configured webhook whenever a song plays.

Vinkius routes your audio URLs and lyric text queries through a V8 Isolate Sandbox. The process runs ephemerally and destroys the environment after the API returns the track metadata. Your local files never leave your machine unless you explicitly upload them to a public URL first.

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