Can I test money flows safely without losing real funds?

Absolutely. Increase has a top-tier sandbox environment. In your MCP settings, pass a Sandbox API Key (starting with `sk_test_`) and optionally set the environment to 'sandbox'. We even implemented literal tool overrides like `increase_simulate_inbound_ach` which are intentionally restricted exclusively to simulating inbound events on your test environment.

Does adding a new account via the Agent require paperwork?

No! Assuming your global LLC has already passed initial onboarding and your Entity object handles compliance, any subsequent programmatic calls to `increase_create_account` yield a fully compliant sub-ledger and associated numbers instantaneously contextually within the UI chat responses.

What is the difference between ACH and Wire transfer arrays here?

ACH acts through clearing houses taking normally 1-3 business days suited perfectly for non-urgent vendor mass payouts (`create_ach`). Wire transfers (`create_wire`) tie directly to Fedwire routing logic hitting banks internally within minutes - often bearing a slight static fee. Dictate which the bot should invoke based on liquidity needs.

How can I trace a specific payment?

We've added `increase_list_transactions` to handle historical booked transfers strictly by ID limits, exposing whether money cleared Fed limits safely.

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

Name: Increase
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 Increase 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="Increase Assistant",
            instructions=(
                "You help users interact with Increase. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Increase"
        )
        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 Increase MCP Server

The Increase MCP Server connects AI to a physical, fully compliant commercial US bank built explicitly top-down for programmatic transactions.

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

What you can do

Endless Provisioning — Instantly generate new live bank accounts increase_create_account acting as sub-ledgers, enabling separate balances.
Open Payment Rails — Need to inject funds into a supplier directly using native American payment streams? Use increase_create_ach or sweep high-value overnight increase_create_wire securely.
Simulation Environment — Use Sandbox arrays to trigger simulated money hits increase_simulate_inbound_ach checking if an external agent script validates receiving deposits before going to production.

The Increase 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 Increase to OpenAI Agents SDK via MCP

Follow these steps to integrate the Increase 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 Increase

Why Use OpenAI Agents SDK with the Increase MCP Server

OpenAI Agents SDK provides unique advantages when paired with Increase 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

Increase + OpenAI Agents SDK Use Cases

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

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

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

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

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

Increase MCP Tools for OpenAI Agents SDK (12)

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

increase_create_account

Spin up a new Bank Account programmatically

increase_create_ach

Push an outbound ACH transfer to any US Bank

increase_create_card

Issue a physical/virtual debit card attached to an account

increase_create_routing_number

Generate new ABA routing & account number data

increase_create_wire

Send a same-day US Wire transfer

increase_get_balance

Fetch realtime ledger balance for a specific account

increase_list_accounts

List all sub-accounts under your charter

increase_list_cards

Sweep the active array of issued Cards

increase_list_transactions

Financial history extraction (Booked)

increase_list_transfers

Audit outbound transfers

increase_simulate_inbound_ach

Simulate receiving an ACH inbound (SANDBOX ONLY)

increase_simulate_inbound_wire

Simulate receiving a Wire inbound (SANDBOX ONLY)

Example Prompts for Increase in OpenAI Agents SDK

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

"Use our main test routing sandbox mechanism to simulate inbound an external payload of $1000 into Account ID 'acc_1234'."

"Audit our entire open accounts layout right now."

"Spin up a new fresh physical corporate banking account dedicated uniquely to 'Server Spends'. Send the Routing number to me."

Troubleshooting Increase MCP Server with OpenAI Agents SDK

Common issues when connecting Increase 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.

Increase + OpenAI Agents SDK FAQ

Common questions about integrating Increase 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.