How to Use the Genius MCP in AutoGen

Q: How do I add the Genius MCP Server to AutoGen?

Install autogen-extmcp. Initialize mcpservertools with a StreamableHttpServerParams URL, then pass the resulting list into your AssistantAgent constructor.

Q: Do AutoGen agents know how to format Genius API requests?

The McpToolAdapter handles all schema conversions automatically. Your agents see standard JSON schemas for tools like getannotation and formulate their inputs accordingly.

Give your AutoGen multi-agent systems the ability to debate song meanings and research discographies.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Genius MCP to AutoGen

Create your Vinkius account to connect Genius 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 Genius with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Lyric Analysis

`get_song` pulls the full text and HTML lyrics for any track. One AutoGen agent reads the raw lyrics, while a secondary agent calls `get_song_annotations` to fetch the community explanations. The two agents debate the meaning of the track. The first agent proposes an interpretation, and the second agent challenges it using the vote counts and author info retrieved from the annotations. They negotiate until they reach a consensus.

Discography Research with the MCP Server

`get_artist_songs` returns paginated lists of tracks and pageview counts. A research agent iterates through the pages to compile a complete list of an artist's catalog. A separate data-validation agent cross-references this list by calling `get_album`. It checks the release dates and track lists to ensure the research agent didn't miss any obscure features or EPs.

Automated Metadata Verification

`search_songs` finds potential matches when agents receive vague titles or partial lyrics. The agents discuss the search results, comparing pageview counts to determine the most likely correct track. Once they agree on a track ID, they execute `get_artist` to pull the artist's IQ score and profile description. The conversation framework ensures no single agent makes a final decision without verifying the data points first.

Setup guide

Set up Genius 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 Genius 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="Genius_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Genius 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="Genius_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Genius 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 Genius. 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 Genius 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 Genius MCP in AutoGen

Install `autogen-ext[mcp]`. Initialize `mcp_server_tools` with a `StreamableHttpServerParams` URL, then pass the resulting list into your `AssistantAgent` constructor.

The `McpToolAdapter` handles all schema conversions automatically. Your agents see standard JSON schemas for tools like `get_annotation` and formulate their inputs accordingly.

They share the same tool definitions, but execution happens sequentially based on the conversation turn. One agent calls `search_songs`, and another analyzes the results.

If a tool call fails, the error message enters the conversation history. The agent reads the failure reason and attempts a different approach, like adjusting the search query.

Information like artist IQ scores, lyric fragments, and album release dates is processed entirely within your local agent conversation loop. The zero-trust architecture means the server cannot read your system state or exfiltrate the debate history.

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