How to Use the Inworld AI MCP in AutoGen

Q: How do AutoGen agents collaborate to clone a voice using Inworld AI?

One agent can analyze a user's audio sample and call clonevoice to start the process. A reviewer agent then calls getvoice to verify the status and approve it for production use.

Q: Can I run real-time voice calls within an AutoGen group chat?

Yes, you can trigger createrealtimecall to establish a WebRTC connection. The group agents can then collectively listen, transcribe the audio, and decide who responds.

Q: How do AutoGen agents handle conflicts when updating an Inworld AI router?

Agents can debate the system prompt changes before calling updaterouter. Once they reach consensus, the designated tool-calling agent executes the update with the agreed-upon configuration.

Let AutoGen agents debate and coordinate dynamic voice cloning and character routing configurations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inworld AI MCP to AutoGen

Create your Vinkius account to connect Inworld AI 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 Inworld AI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent consensus on voice design and cloning

Drafting a prompt using `design_voice` lets your creative AutoGen agent collaborate with critic agents on vocal properties. Stop letting a single prompt dictate your voice outputs without a validation step. Once they agree, the execution agent calls `publish_voice` to make it live. This collaborative loop ensures you only deploy voice profiles that meet your quality standards.

Let AutoGen agents manage complex MCP Server routers

Executing `update_router` dynamically lets your AutoGen manager agent tune character prompts based on live user feedback. Building deep narrative experiences requires constant adjustment of your character logic, which this MCP Server simplifies. If a character gets off-track, the agents can verify the configuration using `get_router` and apply fixes instantly. Your conversational safety guards remain active without manual coding.

Collaborative real-time call coordination

Spinning up a live session using `create_realtime_call` requires tight coordination between your conversational agents. Managing a live voice session requires tight coordination between transcription and synthesis, which this MCP setup handles easily. Parsing user statements happens on the fly using `transcribe_audio`, allowing a third agent to formulate the perfect response. They then stream the audio back using `synthesize_speech_stream`.

Setup guide

Set up Inworld AI 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 Inworld AI 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="Inworld AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent can analyze a user's audio sample and call `clone_voice` to start the process. A reviewer agent then calls `get_voice` to verify the status and approve it for production use.

Yes, you can trigger `create_realtime_call` to establish a WebRTC connection. The group agents can then collectively listen, transcribe the audio, and decide who responds.

Agents can debate the system prompt changes before calling `update_router`. Once they reach consensus, the designated tool-calling agent executes the update with the agreed-upon configuration.

It gives your multi-agent team direct control over speech synthesis and character routing. Agents can dynamically switch voices using `list_voices` based on the flow of the conversation.

All voice profiles and cloning metrics are protected by Vinkius's zero-trust architecture. The server runs in an isolated sandbox, ensuring your private assets are never exposed to other agents or external networks.

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