How to Use the Column MCP in LangChain

Q: Does Column allow a LangChain chain to simulate inbound ACH payments during local tests?

Yes, you call columnsimulateach inside your test suite. This lets you mock deposits and verify your agent's response logic before deploying to production.

Q: How does LangChain handle balance verification before triggering a Column wire transfer?

The agent runs columngetbalance first within its decision loop. It only fires columncreatewiretransfer if the settled funds meet your threshold.

Run real bank accounts inside your LangChain reasoning loops without writing custom API integration code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Column MCP to LangChain

Create your Vinkius account to connect Column 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 Column with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain KYC checks directly into bank account setup

Your LangChain agent registers a business and opens a DDA back-to-back using the Column MCP Server with `column_create_entity`. Pass the output straight into `column_create_bank_account` inside a single run. Stop wasting time writing glue code to pass routing numbers between steps.

Multi-step ACH payment sweeps with LangChain

Pull payment histories and trigger settlement sweeps using `column_list_transfers`. By combining this check with `column_create_ach_transfer`, your chain reads past transactions, calculates outstanding balances, and sends the money out.

Automated paper check mailing from chain logic

When modern routing fails, your LangChain chain falls back to physical mail using `column_create_check`. The agent prints and posts a paper check when an ACH transfer fails or if a vendor requires old-school paper. It reads the balance using `column_get_balance` first to make sure the account is funded. This keeps your automated back-office runs from bouncing checks.

Setup guide

Set up Column 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 Column 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({
    "column-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 Column 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 Column. 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 Column 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 Column MCP in LangChain

Configure your endpoint token inside Vinkius. Your LangChain code connects via the MCP client without exposing raw bank API keys to your local runtime.

Yes, you call `column_simulate_ach` inside your test suite. This lets you mock deposits and verify your agent's response logic before deploying to production.

It does. Because the server exposes standard tools, LangChain automatically logs every `column_get_statement` or transfer call, tracking token costs and latency.

The agent runs `column_get_balance` first within its decision loop. It only fires `column_create_wire_transfer` if the settled funds meet your threshold.

All bank statements, routing details, and KYC profiles remain inside Column's chartered infrastructure. Vinkius runs a zero-trust sandbox that never caches your financial data or account balances.

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