How to Use the KeyPay MCP in OpenAI Agents SDK

Connect your OpenAI Agents SDK to KeyPay to automate payroll data retrieval and employee record management with strict safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KeyPay MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate payroll data with OpenAI Agents SDK

Stop manually jumping between tabs to check pay slips. Your agent uses `list_pay_slips` and `list_pay_runs` to pull financial data directly into your workflow. Everything happens inside your existing agent environment. You get the exact records you need without leaving your terminal or code editor.

Secure employee record access

Your agent handles sensitive employee information by invoking `get_employee_details` only when explicitly required. It keeps the data flow contained and traceable. This MCP Server acts as a bridge for your agent. You maintain full visibility of every request made to the payroll system through your standard diagnostic logs.

Precise pay run reconciliation

Reconcile complex earnings and deductions using `list_pay_run_earnings` and `list_pay_run_deductions`. Your agent parses these records to spot discrepancies before they become payroll headaches. It performs the heavy lifting of data aggregation. You just review the final report produced by your agent's analysis of the raw API output.

Setup guide

Set up KeyPay 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 KeyPay tools at runtime.
3

Create your Agent

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

Run the agent

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

The server exposes KeyPay endpoints as native tools for your agent. Once you pass the server configuration to your agent constructor, the framework automatically maps the payroll methods for immediate use.

Yes. Since your agent uses standard MCP protocols, every call to `get_pay_run_details` or other tools is captured in your OpenAI dashboard traces. You can verify exactly what data was requested and when.

The server provides raw data access, and your agent applies the necessary validation logic. You control the scope of the agent's permissions, ensuring it only touches the specific payroll records you authorize.

Not at all. You define the HTTP connection in your Python script and pass it to the agent. It handles the discovery of all ten payroll tools without extra manual coding.

This server touches PII like employee names and salary figures. It transmits this data directly from the API to your agent's memory, avoiding intermediate storage or logging services.

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