How to Use the AudioStack MCP in AutoGen

Q: How do my AutoGen agents access AudioStack tools?

Use the mcpservertools function from the autogen-extmcp package. This fetches all available AudioStack tools and prepares them for your AssistantAgent. The adapter handles the schema conversions automatically.

Q: Is my script text secure with AutoGen and AudioStack?

It is. When an agent calls the texttospeech tool, your script text is sent to the Vinkius MCP Server. It's processed in a sandboxed, single-use environment, and your input data is not retained after the request finishes.

Build teams of AI agents that collaborate and debate on audio production choices using AudioStack and AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AudioStack MCP to AutoGen

Create your Vinkius account to connect AudioStack 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 AudioStack with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an AI Audio Production Team

This MCP Server lets you give specific audio roles to your AutoGen agents. Create a 'Casting Director' agent that uses `list_voices` to find talent, and a 'Sound Engineer' agent that picks music with `list_sound_templates`. AutoGen makes these agents talk to each other. The Casting Director might challenge a script and suggest a different voice. The Sound Engineer could argue that the chosen music doesn't fit. They debate until they agree on a plan, then execute it with `create_audioform`.

Consensus-Driven Voice Selection

You can make better choices through agent conversation. One agent, the 'Proposer,' can use `list_voices` to suggest a voice for a project based on a prompt. A second agent, the 'Critic,' can then use `get_voice_details` to check the specifics of that voice—its provider, accent, and style—and argue for or against it. This back-and-forth, using live data from the AudioStack tools, leads to a more considered final choice.

Add Guardrails with Specialist AutoGen Agents

Go beyond creative roles. Build a 'Finance' agent whose only job is to monitor costs by calling `get_usage_analytics`. It can participate in the conversation and flag if a project is getting too expensive. This is where AutoGen's multi-agent setup shines. A 'Production' agent might want to run `create_story`, but the 'Finance' agent objects based on the latest usage data. They negotiate a solution, maybe by using a cheaper voice or a shorter script, all before any cost is incurred.

Setup guide

Set up AudioStack 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 AudioStack 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="AudioStack_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the `mcp_server_tools` function from the `autogen-ext[mcp]` package. This fetches all available AudioStack tools and prepares them for your `AssistantAgent`. The adapter handles the schema conversions automatically.

Yes, that's a perfect use case. Create a dedicated agent that only has access to the `get_usage_analytics` tool. It can then join the group chat and warn other agents when they're about to exceed spending limits.

A solid team includes a 'Writer' agent, a 'Casting' agent using `list_voices`, a 'Sound Designer' with `list_sound_templates`, and a 'Producer' that makes the final call with `create_audioform`. They can debate creative choices before committing.

Agents in AutoGen decide based on the conversation and their instructions. If one agent asks, "Find me a British voice," another agent whose prompt defines it as the casting director will know to use the `list_voices` tool with the right filters.

It is. When an agent calls the `text_to_speech` tool, your script text is sent to the Vinkius MCP Server. It's processed in a sandboxed, single-use environment, and your input data is not retained after the request finishes.

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