How to Use the Mercury MCP in OpenAI Agents SDK

Q: How do I connect Mercury bank accounts to the OpenAI Agents SDK?

Install the package using pip install openai-agents and initialize the Mercury server stream. Pass the Vinkius HTTP URL to MCPServerStreamableHttp and add that server object directly to your OpenAI agent's constructor list.

Q: What tools are available in this package?

You get eight read-only tools including listaccounts, listcards, listcustomers, listinvoices, listrecipients, and getaccount. These tools let your OpenAI agents inspect your Mercury financial status without any write access.

Run autonomous financial operations safely using OpenAI Agents SDK to pull live Mercury transaction data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercury MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Balance Monitoring with OpenAI Agents SDK

The `get_balance` tool pulls live ledger balances directly into your OpenAI Agents SDK runtime. Your OpenAI agent inspects current cash positions across your Mercury accounts to trigger automated treasury movements based on real-time numbers. By configuring `cacheToolsList=True` in your Python script, your OpenAI agent holds the Mercury tool schema in memory to speed up balance checks.

Automated Reconciliation via MCP Server

The `list_transactions` tool lets your OpenAI agent pull Mercury transaction history to match against internal ledgers. This MCP Server exposes raw ledger data directly to your Python environment, avoiding manual exports. The OpenAI dashboard logs every single execution of `list_transactions` so you can audit exactly what Mercury data your agent pulled. You maintain a clean paper trail of financial checks without writing custom logging wrapper code.

Vendor Card Audits

The `list_cards` tool exposes active Mercury corporate debit cards to your agent. Your OpenAI agent system inspects card ownership and active status to flag unapproved team spending. When passing `mcp_servers=[server]` to your OpenAI Agent constructor, the SDK auto-discovers this Mercury tool. It allows specialized agents to hand off card audit tasks to your accounting agent with zero manual routing.

Setup guide

Set up Mercury 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 Mercury tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Mercury 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="Mercury Agent",
            instructions="You have access to Mercury 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 Mercury. 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 Mercury 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 Mercury MCP in OpenAI Agents SDK

Install the package using `pip install openai-agents` and initialize the Mercury server stream. Pass the Vinkius HTTP URL to `MCPServerStreamableHttp` and add that server object directly to your OpenAI agent's constructor list.

Yes, the SDK queries the Vinkius MCP Server endpoint at startup to find Mercury tools like `list_transactions` and `get_balance`. You do not need to manually write JSON schemas or register functions in your Python code.

The OpenAI Agents SDK relies on Vinkius's managed MCP Server infrastructure to handle connection pooling and request queues for Mercury. Setting `cacheToolsList=True` in your Python setup reduces unnecessary setup calls to the API.

You get eight read-only tools including `list_accounts`, `list_cards`, `list_customers`, `list_invoices`, `list_recipients`, and `get_account`. These tools let your OpenAI agents inspect your Mercury financial status without any write access.

Your Mercury bank account details, balances, and transaction histories are protected by Vinkius's zero-trust V8 Isolate Sandbox. Every request runs in an ephemeral container that immediately dissolves after executing, meaning your banking credentials are never stored or exposed to external OpenAI models.

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