How to Use the Boathouse Connect MCP in AutoGen

Q: How do I feed Boathouse Connect tools to AutoGen agents?

Use the MCP tool helper with StreamableHttpServerParams pointing to the Vinkius URL. Pass the returned tool list directly into your AssistantAgent constructor.

Q: Can AutoGen agents negotiate Boathouse Connect slip assignments?

Yes, one agent can fetch availability with listschedules while another checks member details using getuser to negotiate the best slip assignment.

Q: How do AutoGen agents handle failed Boathouse Connect actions?

If createreservation returns an error, the executing agent shares the failure message in the conversation thread. The other agents then debate alternative dates based on listschedules.

Q: Do I need to manually map the tool schemas?

No, the McpToolAdapter handles all schema conversions automatically. Your agents will understand the parameter requirements for every tool without manual configuration.

Deploy AutoGen agents to debate and resolve Boathouse Connect slip reservation conflicts.

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 AutoGen

Create your Vinkius account to connect Boathouse Connect to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve Booking Conflicts via AutoGen Debate

The `create_reservation` tool allows your booking agent to secure slips once the manager agent approves the schedule. If a conflict arises, a scheduling agent calls `list_reservations` while a customer agent checks member tier data. They debate the best resolution in an AutoGen group chat before writing the final reservation back to the system. This consensus-driven approach keeps your booking book clean and error-free.

Coordinate Marina Assets with an MCP Server

The `get_equipment` tool provides real-time status updates to your maintenance and booking agents. When an asset is flagged for repair, the maintenance agent alerts the booking agent to reschedule upcoming trips. This MCP Server integration uses the `mcp_server_tools` helper to load these operations into your agents. The schema conversion is handled automatically, so your agents can focus on negotiating schedules.

Verify API Health Before Agent Execution

The `check_boathouse_status` tool lets your supervisor agent verify connection health before starting the multi-agent debate loop. If the API is unreachable, the supervisor pauses the conversation to prevent infinite retry loops. You configure this check using `StreamableHttpServerParams` pointing to your managed Vinkius endpoint. This ensures your agents only execute tasks when the backend is fully operational.

Setup guide

Set up Boathouse Connect MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Boathouse Connect tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Boathouse Connect_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Boathouse Connect data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Boathouse Connect_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Boathouse Connect data")
    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 AutoGen

Use the MCP tool helper with `StreamableHttpServerParams` pointing to the Vinkius URL. Pass the returned tool list directly into your `AssistantAgent` constructor.

Yes, one agent can fetch availability with `list_schedules` while another checks member details using `get_user` to negotiate the best slip assignment.

If `create_reservation` returns an error, the executing agent shares the failure message in the conversation thread. The other agents then debate alternative dates based on `list_schedules`.

No, the `McpToolAdapter` handles all schema conversions automatically. Your agents will understand the parameter requirements for every tool without manual configuration.

All communication with your database is encrypted in transit and executed within zero-trust sandboxes. Your member names and reservation histories are never stored or logged 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