How to Use the Inworld AI MCP in Google ADK

Q: How do I stream audio from Inworld AI using Google ADK?

The agent invokes synthesizespeechstream to receive a continuous audio stream. This works over standard HTTP or Stdio transports supported by the ADK framework.

Q: Is it possible to limit which Inworld tools Gemini can access?

Yes, you can use the toolnames filter in McpToolset to expose only specific tools like synthesizespeechsync or transcribeaudio over this MCP connection.

Connect Inworld AI to your Google ADK pipelines to drive lifelike voice synthesis using Gemini long-context reasoning.

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 Google ADK

Create your Vinkius account to connect Inworld AI to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise voice design via Google ADK

The `design_voice` tool generates unique voice profiles from plain text prompts directly within your Gemini agent loop. Your Google ADK agent executes this tool to create new character voices based on data pulled from BigQuery. Once designed, the agent uses `publish_voice` to make the asset live across your cloud deployment. You can then list all active profiles using `list_voices` to verify deployment status before running production speech tasks.

Dynamic routing with Google ADK MCP Server

The `create_router` tool builds routing configurations that map complex user intents to specific characters. Your agent uses `list_routers` to scan available endpoints and `get_router` to pull detailed character parameters. This MCP Server integration allows Gemini's 1M+ token context window to inform routing decisions. The agent analyzes massive interaction histories from Vertex AI before calling `update_router` to refine the conversational path.

Streaming speech synthesis and transcription

The `synthesize_speech_stream` tool delivers low-latency audio streams directly to your enterprise application. Your Google ADK agent triggers this tool to convert text responses into high-fidelity speech on the fly. For incoming audio, the agent calls `transcribe_audio` to convert speech to text before running analysis. This allows you to store accurate text transcripts directly in BigQuery for downstream analytics.

Setup guide

Set up Inworld AI MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Inworld AI tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Inworld AI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Inworld AI tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use McpToolset with your Vinkius HTTP URL and pass it to your LlmAgent tools list. The MCP Server registers the tools for your Gemini model to call instantly.

Yes, your agent can read voice metadata from BigQuery and use `clone_voice` or `update_voice` to sync profiles with the Inworld platform. This keeps your custom voice library updated automatically.

The agent invokes `synthesize_speech_stream` to receive a continuous audio stream. This works over standard HTTP or Stdio transports supported by the ADK framework.

Yes, you can use the tool_names filter in McpToolset to expose only specific tools like `synthesize_speech_sync` or `transcribe_audio` over this MCP connection.

All prompt text and audio data pass through ephemeral V8 isolates on Vinkius. Google Cloud security standards apply to your ADK environment, ensuring no data leaks outside your project boundaries.

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