How to Use the StayFi MCP in LangChain

Q: What is the best way to monitor multiple property locations with StayFi and LangChain?

Use a chain starting with listproperties to gather all IDs. Then, loop through those IDs, calling getpropertystats for each one. This gives you a structured, comprehensive overview of your entire portfolio.

Q: Can StayFi and LangChain track hardware inventory across properties?

Yes. You can call listdevices to get an initial list of all connected equipment. If you need location context, run this process after calling listproperties, ensuring every device is mapped back to its specific site.

Q: If I want a report on guest data, how does StayFi and LangChain organize the output?

You can combine calls. First, you run exportguests for the raw CSV data. Then, if you need specific metrics, your agent can follow up by calling getanalytics to summarize key trends.

Build multi-step reasoning chains for StayFi using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect StayFi MCP to LangChain

Create your Vinkius account to connect StayFi to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup StayFi with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run Multi-Step Guest Data Workflows with the MCP Server

Need to track a guest's full history? You can chain together calls. For instance, you first call `list_properties` to find all locations, then use `list_guests_by_property` for specific records. Your agent doesn't just run one command; it decides the next step based on the output. It pulls guest details using `get_guest`, and immediately uses that ID to check their network status with `get_device_status`. This allows complex, multi-stage reasoning pipelines.

Aggregate Property Health Checks for LangChain Agents

Managing multiple properties means checking various systems. The agent can first call `list_properties` to get all site IDs. Then it iterates through them, calling `get_network` and `get_property_stats` sequentially for every location. This chained approach lets you build a full system health report automatically. You'll see the connectivity status via `check_stayfi_status`, followed by detailed network reports from `list_networks`. It’s all one continuous, observable process.

Process and Export Full Marketing Datasets

The MCP Server lets you build complete reporting chains. Start by calling `export_guests` to grab raw guest data. Then, use that exported list to verify email collection stats via `get_email_stats`. You can also call `list_splash_pages` and then cross-reference the details using `get_splash_page`. This means you get a full picture: who stayed, what emails were captured, and which marketing pages were served. The entire workflow is traceable through your agent's execution history.

Setup guide

Set up StayFi 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 StayFi 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({
    "stayfi-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 StayFi 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 StayFi. 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 StayFi 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 StayFi MCP in LangChain

LangChain lets you build multi-step logic. You can start by calling `search_guests` with a name, then immediately use that result to pull detailed information using `get_guest`. It chains the requests together so your agent knows exactly what data it has.

Use a chain starting with `list_properties` to gather all IDs. Then, loop through those IDs, calling `get_property_stats` for each one. This gives you a structured, comprehensive overview of your entire portfolio.

Yes. You can call `list_devices` to get an initial list of all connected equipment. If you need location context, run this process after calling `list_properties`, ensuring every device is mapped back to its specific site.

You can combine calls. First, you run `export_guests` for the raw CSV data. Then, if you need specific metrics, your agent can follow up by calling `get_analytics` to summarize key trends.

You'll find tools for both physical assets and digital content. For example, you can list available splash pages with `list_splash_pages` and then retrieve the current live details using `get_splash_page`.

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