How to Use the AcoustID MCP in AutoGen

Q: Can I build an AutoGen team where one agent uses AcoustID to find a song and another verifies it?

Yes, that's a perfect use case. An AssistantAgent can call lookupbyfingerprint, and a UserProxyAgent (or another assistant) can then use getrecordingmetadata to confirm the details before the team accepts the match.

Q: What if my agents only have the song title? Can they still find the AcoustID?

Of course. An agent can use the searchbyrecording tool, passing the title and artist. This is a good first step for an agent conversation, to establish a baseline ID before doing more research.

Build collaborative music analysis agents with AutoGen. Let them debate song metadata, verify matches, and manage your AcoustID library.

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 AutoGen

Create your Vinkius account to connect AcoustID to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Song Matches

This is a perfect job for AutoGen. One agent can use `lookup_by_fingerprint` and propose a match. A second, 'skeptic' agent can then use the returned MusicBrainz ID to call `search_by_recording` with the original artist name to double-check the result. They'll converse until they reach a consensus on the song's identity. You're not just getting a result; you're getting a verified result that's been debated by multiple specialized agents. This reduces errors from low-confidence matches.

Build a Music Curation Team

Create an agent team to manage your music library. An 'Ingestion' agent can use `submit_fingerprint` for new files. A 'Quality' agent could then periodically use `get_recording_metadata` on existing tracks to see if better information has become available. The agents work together, passing information back and forth. The Ingestion agent might ask the Quality agent, 'Should I submit this? The match confidence from the lookup was only 75%.' This creates a much more careful workflow than a simple script.

Negotiate Metadata with this MCP Server

Imagine one agent finds a song with `lookup_by_fingerprint`. A second agent, focused on data completeness, can take the result and call `get_recording_metadata` to check for an album or release date. This is a core function of the AcoustID MCP server. If the metadata is incomplete, the agents can decide on the next steps. Maybe they'll search for a different version using `search_by_mbid`. AutoGen lets your agents negotiate the best approach instead of just following a rigid script.

Setup guide

Set up AcoustID MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes AcoustID tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="AcoustID_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AcoustID data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="AcoustID_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AcoustID data")
    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 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 AutoGen

Yes, that's a perfect use case. An `AssistantAgent` can call `lookup_by_fingerprint`, and a `UserProxyAgent` (or another assistant) can then use `get_recording_metadata` to confirm the details before the team accepts the match.

One agent in the conversation, like a 'SubmitterAgent', would be configured with the `submit_fingerprint` tool. After the team agrees a song is new and should be added, that agent executes the call with the fingerprint and metadata.

This is a great task for AutoGen. One agent can find a MusicBrainz ID, then a 'Researcher' agent can use `search_by_mbid` to find all associated AcoustIDs. The agents can then discuss which version is the correct one for the context.

Of course. An agent can use the `search_by_recording` tool, passing the title and artist. This is a good first step for an agent conversation, to establish a baseline ID before doing more research.

Your agents only exchange audio fingerprint strings and metadata like song titles, not the raw audio. The AcoustID MCP server runs in a dedicated Vinkius sandbox, and access is controlled via a single auth token, keeping your session data isolated.

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