Is it safe to expose my company's payrolls to the AI?

Yes. This connector runs entirely on your local machine or trusted enclave natively. No employee data, payload information or generated queries are routed to our servers—your API interactions occur directly from your environment straight to SmartHR's endpoints.

Can the agent calculate average payroll over time automatically?

Absolutely. Just prompt your agent: 'List all payrolls from Q2, and display the average distribution'. The agent will call the `list_payrolls` endpoint, retrieve the raw figures, do the mathematical operation independently in context, and present you a very clear table or markdown summary.

How do I look up which internal department an employee works for?

You don't need to specify the exact tool. You can simply ask: 'What department is crew member [Name] in?'. Your AI will automatically use the `list_crews` tool and cross reference the results with `list_departments` to formulate a correct response.

SmartHR MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes

Name: SmartHR
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 8 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect SmartHR through 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="SmartHR Assistant",
            instructions=(
                "You help users interact with SmartHR. "
                "You have access to 8 tools."
            ),
            mcp_servers=[mcp_server],
        )

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

Connect your SmartHR directory to any AI agent and empower your team to query employee data, organizational hierarchies, and payroll records securely. Interact with your organization's human capital database through natural language without ever switching tabs.

The OpenAI Agents SDK auto-discovers all 8 tools from SmartHR through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries SmartHR, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Employee Tracking — Call the list_crews tool to retrieve the roster of all employees and cross-reference demographic metadata
Department Hierarchies — Ask your AI to list_departments or check list_positions to understand the internal structure
Deep Employee Profiles — Perform targeted queries using get_crew_details or list_crew_dependents to fetch highly sensitive contract details
Payroll Overviews — Securely query active or historical payroll ledgers to audit compensation scaling

The SmartHR MCP Server exposes 8 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 SmartHR to OpenAI Agents SDK via MCP

Follow these steps to integrate the SmartHR 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 8 tools from SmartHR

Why Use OpenAI Agents SDK with the SmartHR MCP Server

OpenAI Agents SDK provides unique advantages when paired with SmartHR 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

SmartHR + OpenAI Agents SDK Use Cases

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

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

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

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

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

SmartHR MCP Tools for OpenAI Agents SDK (8)

These 8 tools become available when you connect SmartHR to OpenAI Agents SDK via MCP:

get_crew_details

Retrieves details for a specific employee

list_crew_dependents

Lists dependents for a specific employee

list_crews

Lists all employees (crews) in SmartHR

list_departments

Lists all organizational departments

list_employment_types

Lists all employment types

list_establishments

Lists business establishments or office locations

list_payrolls

Lists employee payroll records

list_positions

Lists all job positions or roles

Example Prompts for SmartHR in OpenAI Agents SDK

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

"Fetch the entire roster and list the top 3 job positions that occur most frequently."

"Retrieve the details for crew member `crew-8f192`, including their enrolled dependents."

"List all physical establishments the company operates."

Troubleshooting SmartHR MCP Server with OpenAI Agents SDK

Common issues when connecting SmartHR 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.

SmartHR + OpenAI Agents SDK FAQ

Common questions about integrating SmartHR 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.