How to Use the Envoy MCP in Google ADK

Q: Can Google ADK analyze Envoy delivery logs?

Yes. Your agent can call listdeliveries to pull package logs into Gemini's long-context window. From there, you can cross-reference deliveries with employee schedules to send pickup reminders.

Run your physical office operations by connecting Envoy tools directly to Google ADK agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Envoy MCP to Google ADK

Create your Vinkius account to connect Envoy 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 Envoy with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pre-register office guests via Google ADK

The `pre_register_visitor` tool feeds your visitor schedules directly from BigQuery databases into Envoy. Your Google ADK agent automates guest invites based on enterprise meeting data without manual entry. The agent verifies existing schedules with `list_visitors` to prevent duplicate entries. It acts as an automated receptionist that works directly with your Google Cloud database.

Coordinate hot desks using Gemini long-context reasoning

The `list_desks` tool gives your agent the power to inspect desk inventory across global offices. By calling `reserve_desk`, your agent can organize seating plans for hundreds of employees at once within Gemini's million-token context window. If plans change, the agent invokes `cancel_desk_reservation` to free up the space. This keeps your office footprint optimized without manual spreadsheet tracking.

Expose Envoy MCP Server tools to your Google ADK agent

The `list_locations` tool lets your agent inspect physical office structures. The agent maps out your real estate footprint and coordinates room availability using `list_rooms` alongside desk bookings. You can restrict which tools are exposed by passing a specific list of tool names to the toolset. This ensures your agent only touches the rooms and desks you want it to manage.

Setup guide

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

It's simple. You initialize the toolset using the MCP protocol with the server URL. Then, pass the toolset directly to your LlmAgent instance to let Gemini models call tools like `reserve_desk`.

Yes. Your agent can call `list_deliveries` to pull package logs into Gemini's long-context window. From there, you can cross-reference deliveries with employee schedules to send pickup reminders.

Use the optional tool names filter when initializing your toolset. This lets you expose safe tools like `list_locations` while blocking write operations like `cancel_desk_reservation`.

Yes. The Google ADK toolset handles both transport layers natively. Run the Envoy MCP Server over HTTP for production setups.

Desk reservation details and capacity numbers are processed inside an isolated Vinkius MCP sandbox. No desk-booking data is stored or logged outside of your active Google Cloud execution environment.

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