How to Use the AudD Music Recognition MCP in LangChain

Q: How do I pass AudD Music Recognition tools from this MCP Server to a LangChain agent?

Call client.gettools() on your Vinkius-connected client and pass the list directly to your LangChain agent constructor. The agent will then have access to recognizemusic and getlyrics to run music-matching chains.

Q: Can LangChain trace the latency of AudD Music Recognition calls?

Yes, every call to recognizeattime or searchlyrics shows up in your LangSmith dashboard with full payload details. You can monitor the performance and token usage of each music lookup step.

Q: How does AudD Music Recognition handle long audio files in LangChain?

Your agent uses the recognizeattime tool to query specific timestamps in long-form audio. This keeps your LangChain payloads small and avoids passing massive audio blobs through your LLM context window.

Q: Can I manage webhooks dynamically in a LangChain state machine?

Yes, your graph can use setstreamcallbackurl to change where stream alerts go based on the current run context. This allows you to route different audio streams to distinct processing channels.

Run multi-step audio analysis chains in LangChain with direct access to AudD Music Recognition metadata and lyrics.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipeline raw audio to lyrics in LangChain

The `recognize_music` tool serves as the entry point for your LangChain agents to identify tracks from audio URLs. Your agent can run this tool, grab the track title, and immediately feed it to `get_lyrics` in the next step of the chain. By using this MCP Server, your LangSmith traces capture the exact JSON payload returned from AudD, letting you debug matching errors or API latency in real time. You do not need to write custom parsing code for the song metadata; the agent handles the schema mapping between steps.

Run stream monitors with LangChain agents

The `add_monitored_stream` tool lets your LangChain agent programmatically register live audio feeds using this MCP connection. When a stream matches a track, your configured webhook catches the event, allowing an autonomous agent to decide whether to alert your team or log the play. You can manage these active feeds on the fly using `list_monitored_streams` and `set_stream_callback_url` within a LangGraph state machine. This gives you a self-correcting loop where the agent adds, checks, or updates streams based on incoming webhooks.

Pinpoint tracks in long files with this MCP Server

The `recognize_at_time` tool allows your LangChain chains to target specific offsets inside massive audio files without downloading the entire file. If your agent is processing a two-hour podcast, it can isolate a timestamp and query the music database for that specific moment. Combine this with `search_lyrics` or `search_music` to double-check matches against text fragments. The agent evaluates the confidence scores from the search results to confirm if the identified track matches the context of the audio segment.

Setup guide

Set up AudD Music Recognition MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes AudD Music Recognition tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "audd-music-recognition-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent AudD Music Recognition transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Call `client.get_tools()` on your Vinkius-connected client and pass the list directly to your LangChain agent constructor. The agent will then have access to `recognize_music` and `get_lyrics` to run music-matching chains.

Yes, every call to `recognize_at_time` or `search_lyrics` shows up in your LangSmith dashboard with full payload details. You can monitor the performance and token usage of each music lookup step.

Your agent uses the `recognize_at_time` tool to query specific timestamps in long-form audio. This keeps your LangChain payloads small and avoids passing massive audio blobs through your LLM context window.

Yes, your graph can use `set_stream_callback_url` to change where stream alerts go based on the current run context. This allows you to route different audio streams to distinct processing channels.

Your audio URLs, stream addresses, and lyrics text are processed inside Vinkius's sandboxed V8 isolates. The server never stores your source audio files, keeping your media pipeline private and isolated from other users.

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