How to Use the Monnify MCP in OpenAI Agents SDK

Q: How do I configure the Monnify MCP Server within my OpenAI Agents SDK pipeline?

Install openai-agents and define the server with MCPServerStreamableHttp. Pass it directly into your agent constructor to let it discover tools like reserveaccount dynamically.

Q: How does OpenAI Agents SDK handle Monnify rate limits?

Set cacheToolsList=True in your SDK configuration to prevent redundant schema fetches. For endpoint rate limits on listtransactions, implement standard backoff in your Python agent loop.

Q: Which tool should my agent use to check Nigerian bank codes?

Use listbanks to retrieve the list of supported Nigerian financial institutions. This is crucial for verifying destinations before calling listdisbursements.

Q: How does this MCP integration protect virtual account customer data?

All virtual account details retrieved via getaccountdetails are processed in an ephemeral V8 sandbox. No customer bank details, names, or account numbers are stored on our servers.

Run production OpenAI Agents SDK setups that instantly spin up Monnify virtual accounts and handle Nigerian payments with zero manual code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Monnify MCP to OpenAI Agents SDK

Create your Vinkius account to connect Monnify to OpenAI Agents SDK 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 Monnify with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-Reserve Virtual Accounts via OpenAI Agents SDK

The `reserve_account` tool lets your agent provision dedicated virtual bank accounts for customers on the fly. Since you are using OpenAI Agents SDK, you can set strict guardrails to ensure the agent only triggers this action after verifying the customer's KYC details. Your agent uses `get_account_details` to verify active accounts and `list_reserved_accounts` to audit allocations. The OpenAI dashboard gives you complete trace visibility over these calls, so you can see exactly when and why an account was reserved via this MCP Server.

Track Settlements and Invoices Safely

The `list_settlements` tool provides direct access to merchant settlement histories without leaving your python runtime. When your agent detects a payout delay, it calls `list_monnify_invoices` to check for open balances and match them against incoming payments. By feeding these outputs to specialized sub-agents, you can build a self-healing reconciliation loop. If a settlement looks off, one agent pulls the raw data while another drafts a Slack alert for your finance team.

Initiate Payments with Built-In Guardrails

The `init_payment` tool initiates web checkout transactions directly through your autonomous agent. With this MCP Server, your OpenAI Agents SDK configuration can restrict payment initialization to specific verified user IDs. The agent then monitors the status using `get_transaction` and checks `list_transactions` to confirm the ledger matches. This setup keeps your financial transactions secure while letting the agent handle the heavy lifting.

Setup guide

Set up Monnify MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Monnify tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Monnify tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Monnify tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Monnify Agent",
            instructions="You have access to Monnify tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Monnify. 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 Monnify 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 Monnify MCP in OpenAI Agents SDK

Install `openai-agents` and define the server with `MCPServerStreamableHttp`. Pass it directly into your agent constructor to let it discover tools like `reserve_account` dynamically.

Yes, you can write validation checks that intercept calls to `init_payment` before they execute. This ensures your agent never initializes unauthorized payouts.

Set `cacheToolsList=True` in your SDK configuration to prevent redundant schema fetches. For endpoint rate limits on `list_transactions`, implement standard backoff in your Python agent loop.

Use `list_banks` to retrieve the list of supported Nigerian financial institutions. This is crucial for verifying destinations before calling `list_disbursements`.

All virtual account details retrieved via `get_account_details` are processed in an ephemeral V8 sandbox. No customer bank details, names, or account numbers are stored on our servers.

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