Is 'column_create_check' actually sending out physical US Mail?

Yes! Column natively operates check printing infrastructure lockboxes. By providing a proper US Address in your chat interface to `column_create_check`, Column mechanically generates the cheque deducting the amount initially and mails it sequentially. It is incredibly useful for archaic landlord payouts and contractor duties.

How are Webhooks handled in the AI interaction space?

With `column_list_webhooks`, you give your AI agent deep systemic oversight over what automated routing endpoints are configured to hear back clearance metrics. An AI could check if an engineer correctly connected your primary SaaS billing app to Column's wire settlements.

Does Column authentication require extensive mTLS configurations as well?

No, US Banking BaaS endpoints standardly utilize simpler Auth mappings than LATAM. Column simply relies on Basic Authentication mapping natively your standard alphanumeric `API KEY` which the framework seamlessly encodes securely for you under the hood.

Column MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes

Name: Column
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 12 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Column through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

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

        agent = Agent(
            name="Column Assistant",
            instructions=(
                "You help users interact with Column. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Column"
        )
        print(result.final_output)

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 Column MCP Server

The Column MCP Server effectively bypasses standard FinTech wrappers and ties your artificial intelligence directly to one of the only nationally chartered US banks built originally around raw Developer APIs.

The OpenAI Agents SDK auto-discovers all 12 tools from Column through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Column, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Automated Clearing — Use column_create_ach_transfer to reliably settle recurring vendor payouts directly out of your native balance without relying on external UI web panels.
Establish Corporate Entities — Hook your conversational bots to construct KYC/KYB verified operational clusters column_create_entity ready to map against newly minted bank account numbers (column_create_bank_account).
Physical Check Writing — Astonishing API feature: send literal paper checks natively out to US addresses. Formulate text like "Mail a $40 check to John's address in Texas for maintenance" and the column_create_check prints and bounds the ledger payload directly.

The Column MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK 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 Column to OpenAI Agents SDK via MCP

Follow these steps to integrate the Column MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 12 tools from Column

Why Use OpenAI Agents SDK with the Column MCP Server

OpenAI Agents SDK provides unique advantages when paired with Column through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Column + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Column MCP Server delivers measurable value.

Automated workflows: build agents that query Column, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Column, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Column tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Column to resolve tickets, look up records, and update statuses without human intervention

Column MCP Tools for OpenAI Agents SDK (12)

These 12 tools become available when you connect Column to OpenAI Agents SDK via MCP:

column_create_ach_transfer

Fire an ACH to an external routing/account number

column_create_bank_account

Establish a DDA (Demand Deposit Account)

column_create_check

Very useful for legacy vendor systems. Generate and mail a paper check

column_create_entity

In production, this goes through compliance screening. Register a business or person KYC target inside Column

column_create_wire_transfer

Fire an immediate Wire transfer

column_get_balance

Audit settled funds inside a Bank Account

column_get_bank_account

Fetch specific DDA details (Routing info)

column_get_statement

Retrieve the generated bank statement artifacts

column_list_entities

View all active KYC profiles under the charter

column_list_transfers

Sweep historical ACH payment operations

column_list_webhooks

View all registered listening streams

column_simulate_ach

Trigger Sandbox inbound money movement

Example Prompts for Column in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Column immediately.

"Scan our balance history within my Operational account ID. See exactly how much pure funds are settled and available for dispatch."

"Print out a $1,500 manual paper check paid out to 'Green Construction LLC'. Mail it to '55 Broad St, Chicago IL 60601'."

"Initialize a Same-Day direct ACH batch targeting our landlord accounting info. Execute a $5,000 push towards Counterparty Router 02844 under entity RentalCorp."

Troubleshooting Column MCP Server with OpenAI Agents SDK

Common issues when connecting Column to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Column + OpenAI Agents SDK FAQ

Common questions about integrating Column MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.