How to Use the Boathouse Connect MCP in Pydantic AI

Q: How do I load the Boathouse Connect MCP Server into a Pydantic AI agent?

Install the slim package with MCP support and use the MCPToolset constructor pointing to your Vinkius HTTP URL. Pass this toolset directly into the Agent class via the toolsets parameter.

Q: Can I use Pydantic AI to validate member lists pulled from Boathouse Connect?

Absolutely. When the agent calls listusers, the returned list of member profiles is validated against your schema, ensuring fields like emails and phone numbers conform to your exact standards.

Q: How does the Pydantic AI integration protect our customer records and slip details?

All customer profiles retrieved through getuser are validated in-memory and never written to disk. Vinkius employs an ephemeral, zero-trust sandbox that prevents any persistent logging of your sensitive marina reservation details.

Validate every slip booking and member record at runtime using Pydantic AI with Boathouse Connect.

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 Pydantic AI

Create your Vinkius account to connect Boathouse Connect to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce type-safe marina bookings with Pydantic AI

The Boathouse Connect MCP Server provides structured data that Pydantic AI validates against strict Python schemas. When your agent invokes `create_reservation`, every field—from check-in dates to vessel beam width—is checked before execution. If the underlying API returns unexpected formatting, your Pydantic AI agent catches the validation error immediately rather than proceeding with corrupt data. This prevents bad inputs from ever reaching your physical dock management system.

Audit harbor equipment and schedule structures

The `list_equipment` tool on the Boathouse Connect MCP Server returns the active inventory of boats, motors, and slips to your Pydantic AI agent. This keeps your asset list clean and structured. Our framework parses this data into strongly-typed Pydantic models, verifying fields like serial numbers and maintenance dates. If a record is missing a critical field, the agent flags it instantly, keeping your equipment logs spotless.

Verify member profiles and active locations

The Boathouse Connect MCP Server retrieves membership data via `get_user` to help customer service agents assign premium slips. This ensures only active members get priority docking. Running this cross-reference against `list_locations` ensures the member is assigned to the correct marina zone. Because every step is strictly typed, you can trust that your agent won't accidentally assign a superyacht to a kayak slip.

Setup guide

Set up Boathouse Connect MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "boathouse-connect-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Boathouse Connect tools.",
)

result = await agent.run("List recent Boathouse Connect transactions")
print(result.output)

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 Pydantic AI

Install the slim package with MCP support and use the `MCPToolset` constructor pointing to your Vinkius HTTP URL. Pass this toolset directly into the `Agent` class via the `toolsets` parameter.

The framework raises a validation error at runtime, preventing the agent from operating on dirty data. This ensures your reservation logic for `get_reservation` always remains clean and predictable.

Absolutely. When the agent calls `list_users`, the returned list of member profiles is validated against your schema, ensuring fields like emails and phone numbers conform to your exact standards.

Yes, the toolset supports both Streamable HTTP and SSE transports. This allows your agent to keep a persistent connection open to track changes in `list_schedules` as they happen.

All customer profiles retrieved through `get_user` are validated in-memory and never written to disk. Vinkius employs an ephemeral, zero-trust sandbox that prevents any persistent logging of your sensitive marina reservation details.

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