How to Use the Mio MCP in Google ADK

Q: Can Gemini query call history using Mio and Google ADK?

Yes, your agent can use listcalls to fetch historical logs and getcalldetails to inspect specific metadata. This lets Gemini analyze past conversations using its long-context window.

Q: How do I manage webhooks with Mio inside Google ADK?

You use createwebhook to register new endpoints and listwebhooks to monitor them. This MCP integration lets your agent remove them when they are no longer required using deletewebhook.

Run phone-based workflows and analyze transcripts using Gemini long-context models with the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mio MCP to Google ADK

Create your Vinkius account to connect Mio 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 Mio with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Launch calls using Gemini and Google ADK

`start_ai_call` initiates live voice interactions directly from your Gemini-powered agent. The agent selects a natural-sounding voice using `list_available_voices` and monitors the active line. Once the objective is met, the agent executes `terminate_call` to hang up. This integration pairs the massive 1M+ token context window of Gemini with real-time voice execution. Your agent can digest massive corporate wikis or BigQuery datasets and use that context to guide the conversation dynamically.

Analyze transcripts with BigQuery and Google ADK

`get_call_transcript` retrieves the complete text of any phone interaction for deep analysis. You can pipe this data straight into BigQuery or Vertex AI to track customer trends over thousands of calls. For faster processing, `get_call_summary` extracts the key decisions and action items instantly. Using this MCP Server simplifies your data pipeline. Instead of writing custom ETL code to move voice logs into your Google Cloud environment, your agent fetches the clean text directly and stores it in your cloud warehouse.

Manage communication state with Google ADK

`list_calls` retrieves the historical log of all voice engagements managed by your account. Your agent inspects specific metadata using `get_call_details` to determine if a follow-up is necessary. Before initiating new outreach, the agent checks `get_credit_balance` to ensure the account has sufficient funds. This structured history allows your enterprise agents to maintain continuity. They can review previous interactions via the MCP Server, verify account status with `get_account_info`, and avoid making redundant calls to the same client.

Setup guide

Set up Mio 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 Mio 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="Mio_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Mio 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 Mio. 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 Mio 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 Mio MCP in Google ADK

Install the ADK using pip and register the server using the HTTP transport parameters. You then pass this toolset to your LlmAgent constructor, making all twelve communication tools immediately available to Gemini.

Yes, your agent can use `list_calls` to fetch historical logs and `get_call_details` to inspect specific metadata. This lets Gemini analyze past conversations using its long-context window.

You use `create_webhook` to register new endpoints and `list_webhooks` to monitor them. This MCP integration lets your agent remove them when they are no longer required using `delete_webhook`.

Yes, the ADK supports a tool names filter. You can limit the agent's access to read-only tools like `get_call_transcript` while blocking execution tools like `start_ai_call`.

All voice transcripts and call details are processed within zero-trust V8 isolates. Vinkius secures the MCP connection via a single secure token, ensuring your communication logs are never exposed to external networks or stored permanently.

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