How to Use the Boathouse Connect MCP in LangChain

Q: How do I add Boathouse Connect tools to my LangChain agent?

You install the MCP adapter package and use MultiServerMCPClient pointing to the Vinkius endpoint. Call gettools() on the client and pass the resulting list directly into your LangChain createagent function.

Q: How does LangChain handle multiple Boathouse Connect locations?

The agent calls listlocations first to map out the active marinas. It then passes those specific location identifiers to listreservations to filter the data for your chain.

Q: How is my Boathouse Connect customer data protected?

Member profiles accessed via getuser are processed inside isolated V8 sandboxes. Your reservation records and slip assignments never persist on Vinkius servers, ensuring strict isolation.

Run multi-step LangChain pipelines to reserve boat slips and check marina schedules instantly.

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 LangChain

Create your Vinkius account to connect Boathouse Connect to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Marina Bookings with LangChain Chains

The `create_reservation` tool connects directly to your LangChain agent so it can book slips during live customer chats. Your agent parses the incoming email, grabs the user ID with `get_user`, and immediately books the dock space without you touching a keyboard. LangSmith traces every step of this workflow, showing you the exact inputs and outputs of the reservation run. You see the latency of each tool execution so you can optimize your agent's decision loop.

Coordinate Fleet Schedules via Multi-Step Reasoning

This Boathouse Connect MCP Server exposes `list_schedules` and `get_equipment` to let your agent manage physical assets dynamically. When a member requests a boat, the agent inspects the calendar, checks boat availability, and flags maintenance conflicts. By feeding the output of one tool directly into the next, your LangChain pipeline handles complex logistics. If a boat is flagged as offline, the chain triggers an alternative lookup in a single run.

Validate Marina Operations in Real Time

The `check_boathouse_status` tool lets your agent verify that the API connection is active before firing off heavy data queries. You run this check at the start of your LangChain agent initialization to prevent broken runs when querying `list_locations`. This integration uses the `MultiServerMCPClient` to combine your marina database with other operational tools in your stack. You get a single tool list passed directly to your agent constructor.

Setup guide

Set up Boathouse Connect MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Boathouse Connect tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "boathouse-connect-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Boathouse Connect transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You install the MCP adapter package and use `MultiServerMCPClient` pointing to the Vinkius endpoint. Call `get_tools()` on the client and pass the resulting list directly into your LangChain `create_agent` function.

Yes, by using LangSmith tracing. You can inspect the exact payload sent to `create_reservation` and see the response payload to troubleshoot failed slip bookings.

The agent calls `list_locations` first to map out the active marinas. It then passes those specific location identifiers to `list_reservations` to filter the data for your chain.

Yes, the connection is stateless by default. If you need to maintain conversational context across multiple marina booking steps, use the client session method.

Member profiles accessed via `get_user` are processed inside isolated V8 sandboxes. Your reservation records and slip assignments never persist on Vinkius servers, ensuring strict isolation.

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