How to Use the AcoustID MCP in LlamaIndex

Q: How do I use LlamaIndex and AcoustID to identify songs and index them?

Wrap the AcoustID tools with McpToolSpec. Your LlamaIndex agent can then call lookupbyfingerprint, and the results—song title, artist, IDs—are automatically indexed into your configured vector store.

Q: How does a LlamaIndex agent search AcoustID with just a song name?

It uses the searchbyrecording tool. Your agent passes the name and artist, gets back the AcoustID, and can then use getrecordingmetadata to build a complete, indexable record for your RAG application.

Q: What if I need to add a song that AcoustID doesn't know about?

Your agent can call submitfingerprint. It passes the fingerprint string, duration, and any known metadata. The new AcoustID is returned and can be immediately indexed by LlamaIndex.

Build a searchable index of your music library's metadata using LlamaIndex and AcoustID's fingerprinting tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AcoustID MCP to LlamaIndex

Create your Vinkius account to connect AcoustID to LlamaIndex 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 AcoustID with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Music Knowledge Base

Use LlamaIndex to call AcoustID tools and automatically index the results into a vector store. Run `lookup_by_fingerprint` on a batch of audio files, and the song titles, artists, and MusicBrainz IDs are fed directly into your knowledge base. Now you can ask natural language questions about your music collection. Your RAG application will answer using the actual metadata it indexed from AcoustID, not by hallucinating. It's a direct line from your files to a queryable index.

Query Your Indexed Music Data

LlamaIndex turns API call results into a queryable resource. After using `get_recording_metadata` on your library and indexing the output, you can ask your agent, 'Which albums by this artist do I have?' or 'Show me all my recordings from 1998'. The agent performs a semantic search over the indexed AcoustID data to give you a precise answer. This grounds the agent's responses in facts straight from your music library, retrieved via this MCP server.

Augment LLM Knowledge with the LlamaIndex MCP Server

Connect your LlamaIndex agent to the AcoustID MCP Server to answer questions about music it wasn't trained on. When asked about an unknown track, the agent can generate a fingerprint and call `lookup_by_fingerprint` to get the answer in real time. The tool's output becomes context for the LLM's final answer. This blends live API data with the model's general knowledge, which is the core of a good RAG system. Your agent now knows about music released yesterday.

Setup guide

Set up AcoustID MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all AcoustID MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to AcoustID tools.",
)
response = await agent.run("List recent AcoustID data")

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 AcoustID. 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 AcoustID 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 AcoustID MCP in LlamaIndex

Wrap the AcoustID tools with `McpToolSpec`. Your LlamaIndex agent can then call `lookup_by_fingerprint`, and the results—song title, artist, IDs—are automatically indexed into your configured vector store.

Yes. Once your agent has a MusicBrainz ID for a track, it can use the `search_by_mbid` tool. The results are then indexed, creating a link between all known audio fingerprints for that song in your knowledge base.

It uses the `search_by_recording` tool. Your agent passes the name and artist, gets back the AcoustID, and can then use `get_recording_metadata` to build a complete, indexable record for your RAG application.

Your agent can call `submit_fingerprint`. It passes the fingerprint string, duration, and any known metadata. The new AcoustID is returned and can be immediately indexed by LlamaIndex.

The server only sees the specific data your agent sends, like audio fingerprint strings or track titles. Vinkius isolates each MCP server session in a zero-trust environment, and all requests are authenticated. The underlying audio files are never transmitted.

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