Can I automatically fetch raw PDF files of individual payslips?

Currently the AI fetches structured JSON metadata representing the explicit payslip limits generated in the pay run, rather than arbitrary PDF media binaries. This ensures high-speed, secure token-based programmatic observation.

Do I need special scopes permitted via PayFit's platform security?

Yes. Ensure the API token generated internally on PayFit's Admin panel is bound physically to 'Collaborators', 'Payslips', and 'Accounting' read boundaries. Without the proper scope, the endpoints strictly deny payloads.

How do accounting entries handle multiple logical company subsidiaries?

The tool bounds its exact logic based directly on the explicit `Company ID` provided in the plugin settings. To query disparate subsidiaries, adjust the Company ID dynamically.

PayFit MCP Server for OpenAI Agents SDK 7 tools — connect in under 2 minutes

Name: PayFit
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 7 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect PayFit 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="PayFit Assistant",
            instructions=(
                "You help users interact with PayFit. "
                "You have access to 7 tools."
            ),
            mcp_servers=[mcp_server],
        )

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

Bring PayFit Global Payroll into your automated AI workflows natively. Providing a strict programmatic bridge to your company's HR and accounting infrastructure, this agent dynamically maps active employees, monitors valid compliance contracts, securely extracts monthly payslip distributions, and generates valid accounting entries directly via chat.

The OpenAI Agents SDK auto-discovers all 7 tools from PayFit through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries PayFit, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Company Overview — Identify exact corporate metadata determining mapping addresses, strict payroll limits, and department structures implicitly
Collaborator Navigation — Locate specific team boundaries, retrieving exactly which individual holds which contract running securely across active modules
Payslip Operations — Identify discrete payslip runs fetching securely masked data tracking payroll compliance outputs
Ledger Generation — Execute direct extractions generating valid mapping endpoints matching automated accounting metrics and financial records

The PayFit MCP Server exposes 7 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 PayFit to OpenAI Agents SDK via MCP

Follow these steps to integrate the PayFit 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 7 tools from PayFit

Why Use OpenAI Agents SDK with the PayFit MCP Server

OpenAI Agents SDK provides unique advantages when paired with PayFit 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

PayFit + OpenAI Agents SDK Use Cases

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

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

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

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

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

PayFit MCP Tools for OpenAI Agents SDK (7)

These 7 tools become available when you connect PayFit to OpenAI Agents SDK via MCP:

get_accounting_entries

Get accounting entries for a specific payroll period (YYYYMM format)

get_collaborator_details

Get detailed information about a specific collaborator

get_company

Get overview information about the PayFit company account

list_collaborators

List all collaborators (employees) in the company

list_contracts

List all employment contracts in the company

list_departments

List all departments in the company

list_payslips

List all payslips for a specific collaborator

Example Prompts for PayFit in OpenAI Agents SDK

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

"Fetch the metadata configuration belonging to our main running PayFit company entity."

"Scan our active architecture fetching a strict list of all collaborators and contracts."

"Retrieve global accounting transactions executed during March."

Troubleshooting PayFit MCP Server with OpenAI Agents SDK

Common issues when connecting PayFit 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.

PayFit + OpenAI Agents SDK FAQ

Common questions about integrating PayFit 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.