How do I request FareHarbor API access?

API access is not public. You must email support@fareharbor.com with your business use case to receive your unique App Key and User Key.

Is there a sandbox environment for testing?

Yes, FareHarbor provides a demo environment at demo.fareharbor.com. You can use this host with your sandbox credentials to test bookings safely.

What is a 'shortname' in FareHarbor?

A shortname is a unique identifier for a specific tour operator or company on the FareHarbor platform. You can find it in the company metadata or dashboard.

FareHarbor MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: FareHarbor
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect FareHarbor through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to FareHarbor "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in FareHarbor?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About FareHarbor MCP Server

Connect your FareHarbor affiliate or partner account to any AI agent and take full control of your tour and activity bookings through natural conversation.

Pydantic AI validates every FareHarbor tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Operator Discovery — List all authorized tour companies and operators in your network
Live Inventory Access — Query specific tours (items) and check real-time availability for any date or range
Seamless Booking — Create new bookings with customer details and ticket types directly from the cloud
Availability Inspection — Fetch granular details for specific time slots including pricing and remaining capacity
Booking Management — List recent bookings and retrieve detailed status by UUID flawlessy
User Context — Verify your API application and user identity credentials through the agent

The FareHarbor MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect FareHarbor to Pydantic AI via MCP

Follow these steps to integrate the FareHarbor MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from FareHarbor with type-safe schemas

Why Use Pydantic AI with the FareHarbor MCP Server

Pydantic AI provides unique advantages when paired with FareHarbor through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your FareHarbor integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your FareHarbor connection logic from agent behavior for testable, maintainable code

FareHarbor + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the FareHarbor MCP Server delivers measurable value.

Type-safe data pipelines: query FareHarbor with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple FareHarbor tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query FareHarbor and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock FareHarbor responses and write comprehensive agent tests

FareHarbor MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect FareHarbor to Pydantic AI via MCP:

create_booking

Create a new booking for a tour or activity

get_availability

Get details for a specific availability slot

get_booking

Get details for a specific booking by UUID

get_item_details

Get details for a specific tour or activity

get_me

Get current API user/affiliate identity

list_availabilities_by_date

List available slots for an item on a specific date

list_availabilities_by_range

List available slots for an item within a date range

list_bookings

List recent bookings for a company

list_companies

List all companies (operators) authorized for booking

list_items

List all tours or activities (items) for a specific company

list_lodgings

List lodging/pickup locations for a company

Example Prompts for FareHarbor in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with FareHarbor immediately.

"List the tour companies I can book for."

"Check availability for the Whale Watching tour tomorrow."

"Show me the details for booking UUID abc-123."

Troubleshooting FareHarbor MCP Server with Pydantic AI

Common issues when connecting FareHarbor to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

FareHarbor + Pydantic AI FAQ

Common questions about integrating FareHarbor MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your FareHarbor MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.