How to Use the ElevenLabs MCP in AutoGen

Q: How do I expose ElevenLabs tools to my AutoGen swarm?

Install autogen-extmcp. Load the tools using mcpservertools and pass the list directly into your AssistantAgent constructor. The adapter handles the schema translation.

Let your AutoGen agents debate and manage ElevenLabs voice assets autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ElevenLabs MCP to AutoGen

Create your Vinkius account to connect ElevenLabs 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 ElevenLabs with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate audio production via MCP

AutoGen agents do not just execute commands blindly. By connecting this MCP Server, you can assign one agent to write a script and another to critique it. Once they agree on the final draft, a dedicated production agent calls `text_to_speech` to generate the actual file. The debate extends to voice selection. A creative agent might suggest a specific persona from `list_voices`, while a quality assurance agent checks `list_models` to ensure the newest neural engine is used. They negotiate the parameters before spending a single character of your quota.

Enforce budgets across AutoGen swarms

Running autonomous agents can drain your API credits if left unchecked. You can build a financial oversight agent that specifically monitors `get_subscription_info` and `get_account_info`. It tracks character usage across the entire swarm. If the swarm approaches its limit, the oversight agent intervenes. It can block other agents from calling generation tools or force them to reuse existing files via `list_audio_history` and `get_download_link`. You get autonomous cost control built directly into the conversation flow.

Maintain strict voice governance

Temporary voice clones pile up fast when multiple agents experiment with audio via MCP tools. A designated cleanup agent can review the current workspace using `get_voice` and `get_voice_settings`. It identifies test clones that are no longer actively used. When it finds an abandoned test clone, the agent runs `delete_voice` to remove the clutter. It also scrubs sensitive test recordings by calling `delete_history_item`. Your AutoGen system maintains a clean, compliant environment without you ever logging into a developer dashboard.

Setup guide

Set up ElevenLabs 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 ElevenLabs 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="ElevenLabs_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]`. Load the tools using `mcp_server_tools` and pass the list directly into your `AssistantAgent` constructor. The adapter handles the schema translation.

Yes. You give multiple agents access to the available voice list. They will discuss the tone of the script and agree on a specific voice ID before generating the audio.

Create a specialized agent that checks your subscription info before any generation happens. It acts as a gatekeeper, rejecting requests if your character balance drops too low.

No. The tools return a direct URL. Your agents can read that URL and write a quick Python snippet in the chat to save the mp3 file locally.

Your swarm sends raw text and receives audio metadata through an isolated Vinkius sandbox. The connection is zero-trust and ephemeral. To enforce strict privacy, have an agent permanently erase the audio logs from the external provider after downloading.

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