How do I get my Mercury API token?

Log in to your Mercury account at app.mercury.com. Go to **Settings → API Tokens** and click **Create Token**. Choose the token type (Read Only for balance checks, or Read and Write for managing recipients). Copy the token immediately — it will only be shown once. Paste it into the configuration field below, and you're ready. No code, no SDK, no webhooks.

Can my AI agent check my startup's runway instantly during a board meeting?

Absolutely. Just ask your AI agent 'What's my current balance across all Mercury accounts?' and it returns real-time balances for every account — checking, savings, and treasury — in seconds. No tab-switching, no logging in, no waiting for the dashboard to load.

What if I need to review recent transactions for month-end close?

Ask your AI agent to pull transactions from any date range. It retrieves each transaction with amount, counterparty, status, and date — perfect for reconciliation. You can filter by account, ask for Wire vs ACH breakdowns, or request only transactions above a specific threshold, all without exporting CSVs.

Is this suitable for companies with multiple Mercury accounts?

Yes. The integration retrieves data across all accounts linked to your API token — operating accounts, savings accounts, and treasury balances. Perfect for venture-backed startups managing multiple entities, holding companies, or finance teams tracking cash positions across subsidiaries.

Mercury MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Mercury
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Mercury through the 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="Mercury Assistant",
            instructions=(
                "You help users interact with Mercury. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

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

Connect your Mercury business banking account to your AI agent and manage your startup finances conversationally.

The OpenAI Agents SDK auto-discovers all 10 tools from Mercury through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Mercury, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Account Balances — Check real-time balances across all your Mercury accounts instantly from your AI agent.
Transaction History — Pull recent transactions filtered by date, amount, or counterparty to track spending patterns.
Recipient Management — List, create, and manage payment recipients for ACH and wire transfers.
Account Details — Retrieve routing numbers, account numbers, and account metadata programmatically.

The Mercury MCP Server exposes 10 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 Mercury to OpenAI Agents SDK via MCP

Follow these steps to integrate the Mercury 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 10 tools from Mercury

Why Use OpenAI Agents SDK with the Mercury MCP Server

OpenAI Agents SDK provides unique advantages when paired with Mercury 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

Mercury + OpenAI Agents SDK Use Cases

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

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

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

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

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

Mercury MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Mercury to OpenAI Agents SDK via MCP:

create_recipient

Required for sending payments. Create a new payment recipient

get_account

Get bank account details

get_transaction

Get transaction details

get_treasury_balance

Get treasury balance overview

list_accounts

List all Mercury bank accounts

list_payments

List sent payments

list_recipients

List payment recipients

list_statements

List bank statements

list_team_members

List all team members

list_transactions

List recent transactions

Example Prompts for Mercury in OpenAI Agents SDK

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

"What's the current balance on all my Mercury accounts?"

"Show me all transactions above $5,000 from this month."

"List all my payment recipients."

Troubleshooting Mercury MCP Server with OpenAI Agents SDK

Common issues when connecting Mercury 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.

Mercury + OpenAI Agents SDK FAQ

Common questions about integrating Mercury 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.