How to Use the Magic Minutes MCP in Google ADK

Q: How do I configure Magic Minutes with Google ADK?

Install the pip package and set up McpToolset with your endpoint URL. Pass the toolset directly to your LlmAgent initialization. The agent will recognize the meeting tools on boot.

Q: How does Gemini handle long transcripts from Magic Minutes?

The framework feeds the output of getmeetingminutes straight into Gemini's long-context window. You load dozens of transcripts simultaneously without hitting token limits.

Feed massive meeting transcripts into Gemini using Google ADK and the Magic Minutes MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Magic Minutes MCP to Google ADK

Create your Vinkius account to connect Magic Minutes 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 Magic Minutes with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse months of meetings with Google ADK

The integration exposes `get_meeting_minutes` to Gemini's massive million-token context window. Your agent pulls raw transcripts from dozens of meetings at once. You cross-reference those conversations directly with your BigQuery datasets. Calling `list_meetings` lets your agent map out your entire calendar history. The Google framework handles the heavy computational lifting of reasoning over all that text. You get actual answers instead of summarized fluff.

Automate enterprise task delegation

Your Gemini agent triggers `create_task` when it identifies a pending action item in the transcript. It verifies the assignee by calling `list_meeting_attendees`. You stop manually parsing who agreed to what. You initialize the connection using `McpToolset` and pass it to your LlmAgent. The server supports both Stdio and HTTP transports. You restrict which tools the agent sees using the tool names filter.

Audit your MCP Server webhooks and health

Enterprise deployments require monitoring, so your agent runs `check_api_health` to verify uptime. It also uses `list_webhooks` to map out where meeting notifications get sent. You keep full visibility into the system state. If you need user context, `get_current_user` pulls the authenticated profile. The agent then calls `list_folders` to organize the generated minutes in your workspace. Everything runs natively within your Google Cloud infrastructure.

Setup guide

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

Install the pip package and set up `McpToolset` with your endpoint URL. Pass the toolset directly to your `LlmAgent` initialization. The agent will recognize the meeting tools on boot.

You pass a specific tool names filter when setting up the toolset. This restricts Gemini from calling tools like `create_task` if you only want it reading data.

The framework feeds the output of `get_meeting_minutes` straight into Gemini's long-context window. You load dozens of transcripts simultaneously without hitting token limits.

The agent reads your meeting data through the MCP tools and natively joins that information with your existing BigQuery tables. You write the logic, and the framework handles the routing.

The server accesses highly sensitive calendar invites and verbatim transcripts. Vinkius isolates every request inside a zero-trust architecture. You authenticate with a single endpoint token, keeping your Google Cloud environment separated from the tool execution.

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