How to Use the FareHarbor MCP in LangChain

Q: How do I handle rate limits when using FareHarbor with LangChain?

LangChain agents can chain getavailability with local caching steps to minimize API hits. You can trace these calls in LangSmith to monitor exact latency and prevent your loops from hitting FareHarbor throttle thresholds.

Q: Can a LangChain agent book tours on FareHarbor automatically?

Yes, your agent can run createbooking directly inside a chain. It takes the output from listavailabilitiesbyrange and passes the required variables to execute the reservation instantly.

Q: How does LangChain pass company IDs to the FareHarbor MCP Server?

The agent first calls listcompanies to identify the correct operator ID. It then passes that ID as an input variable to subsequent tools like listitems in the chain.

Run multi-step booking pipelines in LangChain using direct live inventory lookups and automated reservations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FareHarbor MCP to LangChain

Create your Vinkius account to connect FareHarbor 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 FareHarbor with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain real-time inventory checks to booking execution

The `get_availability` tool queries exact slots directly within your LangChain run, feeding live data straight to the next chain step. Your agent checks real-time slots, grabs the required ID, and immediately triggers `create_booking` without manual steps in between. Langsmith traces the entire sequence so you see exactly how many tokens the agent used when querying `list_availabilities_by_date`. You get clear visibility into every API call, ensuring your booking chains run fast and don't hit rate limits.

Map and trace tour operators in LangChain pipelines

The `list_companies` tool lets your LangChain agent scan all authorized tour operators to find the correct merchant ID before running booking queries. This prevents hardcoded ID errors when your pipeline needs to route bookings across different regional operators. Once the agent finds the operator, it runs `list_items` to fetch the active tours and feeds those tour IDs directly into your LangChain decision tree. The entire flow runs inside a single, observable ReAct loop.

Build multi-step LangChain MCP Server workflows

This MCP Server exposes `list_bookings` to let your LangChain agent inspect recent reservations and resolve customer booking issues in a single execution loop. The agent retrieves the booking payload, extracts customer details, and decides the next logic branch based on actual API data. By combining `get_booking` with your existing database tools in LangChain, you create self-correcting workflows that run without human intervention. You get a reliable pipeline that updates internal databases and FareHarbor simultaneously.

Setup guide

Set up FareHarbor 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 FareHarbor 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({
    "fareharbor-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 FareHarbor 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 FareHarbor. 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 FareHarbor 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 FareHarbor MCP in LangChain

LangChain agents can chain `get_availability` with local caching steps to minimize API hits. You can trace these calls in LangSmith to monitor exact latency and prevent your loops from hitting FareHarbor throttle thresholds.

Yes, your agent can run `create_booking` directly inside a chain. It takes the output from `list_availabilities_by_range` and passes the required variables to execute the reservation instantly.

The agent first calls `list_companies` to identify the correct operator ID. It then passes that ID as an input variable to subsequent tools like `list_items` in the chain.

Yes, the server runs stateless by default. You can use the LangChain MCP adapter to initialize tools for single-run execution loops.

Your booking UUIDs, customer names, and lodging locations accessed via `list_lodgings` stay inside your local LangChain execution environment. Vinkius runs the server in a secure, isolated sandbox that never stores or logs your payload data.

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