How to Use the Uniconta MCP in OpenAI Agents SDK

Q: What data types can I access with Uniconta and OpenAI Agents SDK?

You get access to core financial records: debtor invoices (listdebtorinvoices), GL accounts, and basic customer/vendor lists. The server exposes the necessary endpoints for your agent to work with.

Q: If I need employee data in Uniconta, can OpenAI Agents SDK handle it?

Absolutely. You just call listemployees. Your agent figures out how to pull that list and pass the necessary details back into your Python script.

Run complex ERP logic on Uniconta using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Uniconta MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Full Customer and Vendor Details

You can fetch specific customer data by calling `get_debtor_details`. You also pull a comprehensive list of all registered customers with `list_debtors`. It's useful for validating transactions. The system gives you the full roster of vendors using `list_creditors`, letting your agent confirm who needs payment.

Manage GL Accounts and Journals

Need to check the books? Call `list_gl_accounts` to see every General Ledger account. You can also pull a history of entries using `list_daily_journals`, giving you an audit trail. This helps your agent track where money moves in Uniconta, making sure all financial records are accounted for.

Check Inventory and Employee Roster

The agent pulls product catalog data using `list_inventory_items`. This list shows the current status of every item you sell or use. You'll also find employee records when running `list_employees`, which is critical for payroll processes that need to happen within the Uniconta system.

Setup guide

Set up Uniconta 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 Uniconta tools at runtime.
3

Create your Agent

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

Run the agent

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

The MCP Server lets your agent interact directly with Uniconta's operational data. You use Python to call tools like `list_debtors` inside an async context manager, keeping the connection clean and reliable.

Yeah, it does. Because you're building a production agent system, the built-in guardrails validate every action before execution. This means if an operation fails in Uniconta, your agent catches it immediately.

You get access to core financial records: debtor invoices (`list_debtor_invoices`), GL accounts, and basic customer/vendor lists. The server exposes the necessary endpoints for your agent to work with.

Absolutely. You just call `list_employees`. Your agent figures out how to pull that list and pass the necessary details back into your Python script.

This server touches customer, vendor, journal, and GL account data. Specifically, you can retrieve debtor invoices using `list_debtor_invoices`.

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