How to Use the Square MCP in LangChain

Q: How does LangChain handle complex reconciliation across different locations?

You can build a chain that first uses liststorelocations to identify all sites. Then, the agent iterates over those locations, calling searchorders for each one. This structured approach ensures you account for every physical point of sale.

Q: Can I use LangChain to verify inventory before processing an order?

Absolutely. You can set up a chain that first calls listcatalog to check item availability, and then passes those results into a payment workflow using createpayment. This guarantees you don't process sales for items that are out of stock.

Build Multi-Step Reasoning Pipelines with LangChain and the Square MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Square MCP to LangChain

Create your Vinkius account to connect Square 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 Square with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chaining Payments and Customer Data

The `create_payment` tool starts a multi-step chain. You pass initial payment data, and the resulting transaction ID becomes the input for checking `get_payment_details`. This allows your agent to automatically validate payments before logging them.

Coordinating Inventory Checks

`list_store_locations` gives you all sites. You then feed those IDs into the `search_orders` tool to check specific branch activity. This lets your ReAct agent build a complete picture of sales across multiple physical points.

Finding Specific Customers

The `list_customers` tool provides all records for an account. If you only need one, the `search_customers` tool filters that list down to a single target. This ability makes sure your agent doesn't waste tokens sifting through irrelevant data.

Setup guide

Set up Square 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 Square 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({
    "square-alternative-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 Square 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 Square. 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 Square 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 Square MCP in LangChain

You can build a chain that first uses `list_store_locations` to identify all sites. Then, the agent iterates over those locations, calling `search_orders` for each one. This structured approach ensures you account for every physical point of sale.

The output from an initial tool call always feeds into the next step in your chain. For example, getting a Payment ID via `create_payment` gives you the precise input needed for `get_order_details`. The entire process is observable within the LangSmith trace.

Absolutely. You can set up a chain that first calls `list_catalog` to check item availability, and then passes those results into a payment workflow using `create_payment`. This guarantees you don't process sales for items that are out of stock.

Yes, the MCP Server supports multiple search endpoints. You can combine `search_customers` with `list_payments` in a sequence to build a cross-reference report that standard APIs wouldn't easily connect.

The server touches payment transaction metadata, including customer IDs and specific order details. Remember to handle all sensitive financial information securely when building your LangChain pipelines.

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