How to Use the Boathouse Connect MCP in Google ADK

Q: Can my Gemini agent verify API connectivity before running reservation tasks?

Your agent can run checkboathousestatus at startup to confirm the marina API is responsive. This prevents the agent from attempting complex operations if the physical server is undergoing maintenance.

Q: Where is my marina's reservation and customer data stored during execution?

Customer records retrieved via listusers are processed in memory within your secure Google Cloud VPC. Vinkius acts as a zero-trust bridge, passing the encrypted payload directly to your ADK agent without persisting any slip reservation details on external servers.

Connect Google ADK to Boathouse Connect to run your marina with long-context Gemini reasoning and BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Boathouse Connect MCP to Google ADK

Create your Vinkius account to connect Boathouse Connect 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 Boathouse Connect with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze marina schedules using Google ADK

The Boathouse Connect MCP Server links your harbor operations directly to Google's enterprise agent framework. Your Google ADK agent runs `list_schedules` to inspect dock availability across months of historical reservation data. By using Gemini's million-token context window, the agent processes complex dock layouts returned by `list_locations`. It cross-references this physical layout with active bookings to find optimal slip assignments.

Sync harbor reservations with enterprise data

The `list_reservations` tool on the Boathouse Connect MCP Server lets your Google ADK agent pull active bookings to compare them against your BigQuery revenue tables. This makes financial reporting on slip rentals instant. When a customer calls to modify their stay, the agent uses `get_reservation` to pull the specific booking details. It updates the record and can trigger a Google Cloud function to sync the change across your entire Google Cloud setup.

Manage fleet equipment and member directories

The Boathouse Connect MCP Server tracks physical assets and customer profiles using tools like `list_equipment` inside your Google ADK pipelines. This connects your physical harbor to your digital agent tools. If a member reports a broken utility pedestal, the agent retrieves their profile via `get_user` and matches it to the faulty gear using `get_equipment`. This allows your Gemini agent to automatically draft a maintenance ticket with accurate location data.

Setup guide

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

You start by installing the google-adk package and importing the `McpToolset`. Pass your Vinkius HTTP endpoint to `StreamableHttpServerParameters` and feed that toolset directly into your `LlmAgent`.

Yes, you can use the optional tool names filter when setting up your `McpToolset`. This allows you to expose read-only tools like `list_locations` while hiding write operations like `create_reservation`.

Gemini's large context window allows the ADK agent to ingest the entire output of `list_reservations` in a single pass. It can then reason over hundreds of active boat slips without hitting token limits or losing track of details.

Your agent can run `check_boathouse_status` at startup to confirm the marina API is responsive. This prevents the agent from attempting complex operations if the physical server is undergoing maintenance.

Customer records retrieved via `list_users` are processed in memory within your secure Google Cloud VPC. Vinkius acts as a zero-trust bridge, passing the encrypted payload directly to your ADK agent without persisting any slip reservation details on external servers.

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