How to Use the Mercury MCP in OpenAI Agents SDK

Connect your OpenAI Agents SDK to your Mercury treasury. Automate transaction tracking and recipient management with native guardrails.

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

Automated treasury monitoring

Your agent pulls real-time data using `get_treasury_balance` and `list_accounts`. This gives the SDK immediate visibility into your cash position without manual dashboard hopping. Keep your logic tight by wrapping these calls in your existing agent guardrails. You'll catch anomalies before they hit your ledger.

Secure recipient management

Trigger `create_recipient` directly from your agent's decision loop. The SDK handles the heavy lifting while you define the validation layers. Always gate this behind your internal approval workflow. You maintain control while the agent handles the data entry.

Transaction audit trail

Run `list_transactions` to feed your agent's context window with the latest financial activity. It's the fastest way to build an audit-ready system. Use `get_transaction` when you need to pull specific details for a deep dive. The integration works seamlessly with the OpenAI Agents SDK event loop.

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

The server connects via the MCPServerStreamableHttp interface. You pass it directly into the Agent constructor to enable tool discovery.

Yes, you control the tool set passed to the agent. You can explicitly include or exclude specific functions to maintain strict access policies.

Your data remains isolated within the Vinkius sandbox. The agent only receives the specific information it requests via the allowed tool set.

It does. The implementation uses async context managers, making it a natural fit for the Python-based architecture of the SDK.

The server provides raw transaction records including amounts, timestamps, and metadata. You define the logic for how the agent processes this financial information.

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