How to Use the Buk MCP in OpenAI Agents SDK

Run production-grade HR operations by connecting Buk to your OpenAI Agents SDK with strict guardrails and full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Buk MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure HR actions in OpenAI Agents SDK

Production agents need guardrails before they touch sensitive corporate data. This integration lets you safely run `approve_leave` or `create_employee` through your OpenAI system. You set the execution boundaries, and the SDK handles validation before any payload hits the live server. If an agent tries to execute `delete_employee` without proper authorization, the SDK blocks the action instantly. You get clean, traceable logs on your dashboard instead of silent failures or unauthorized database wipes.

Live payroll and attendance tracking

Pulling compensation metrics shouldn't require manual script writing. Your agent calls `get_payroll` and `get_attendance` directly to build instant snapshots of your workforce status. It maps the returned data directly to specialized agents designed for financial analysis. This setup keeps your general-purpose agents blind to sensitive salary figures. Only your designated payroll agent gets access to the tools, keeping your corporate compliance intact.

Automate onboarding with this MCP Server

New hires require immediate setup across multiple systems. This MCP Server lets your agent run `list_jobs` to match a candidate's profile, then invoke `create_employee` to provision their identity. Once the profile is live, the agent pulls `list_benefits` to map out their standard corporate perks. It handles the entire onboarding sequence without human intervention.

Setup guide

Set up Buk 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 Buk tools at runtime.
3

Create your Agent

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

Run the agent

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

You pass your Vinkius endpoint token directly into the MCPServerStreamableHttpParams constructor. The SDK manages the handshake, meaning your agent doesn't need to store raw HR API keys.

Yes, you control tool exposure at the agent constructor level. You can restrict sensitive tools like delete_employee to specific, highly-guarded agents while letting general agents use list_departments.

Set cacheToolsList=True in your server configuration. This prevents the SDK from querying the server schema on every single turn, reducing latency when fetching get_company_stats.

The SDK catches the error and feeds the raw API response back to the agent. Your agent can then decide to retry the action or escalate the issue to a human manager.

Your HR and payroll records are protected by Vinkius's zero-trust sandboxing. Sensitive payloads from tools like get_payroll pass through ephemeral, isolated environments that never store your company's data.

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