How to Use the Flatwork ATS MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle candidate creation in Flatwork ATS?

The agent calls the createapplicant tool with a structured JSON payload containing the candidate details. The SDK validates the schema before sending it, ensuring your database remains free of corrupt formatting.

Q: How is candidate personal data secured when using this MCP Server?

All applicant details retrieved via getapplicant run through an ephemeral V8 sandbox. We never store candidate resumes, names, or email addresses on our servers, ensuring your hiring data remains private.

Run multi-agent hiring pipelines with guardrails using the OpenAI Agents SDK and Flatwork ATS MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flatwork ATS MCP to OpenAI Agents SDK

Create your Vinkius account to connect Flatwork ATS 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 Flatwork ATS with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Safe Status Changes via OpenAI Agents SDK

The `update_application_status` tool lets your agent move candidates through stages without manual recruiter intervention. Because the OpenAI Agents SDK enforces guardrails, your agent checks candidate qualifications before executing a status change. This MCP Server keeps your pipeline clean. You set the rules in Python, and the agent executes the transition. It reads from `list_applicants` to find candidates who passed the technical test, then updates their status instantly.

Auto-Discover Flatwork ATS Tools Instantly

The `list_jobs` tool exposes active job postings directly to your agent network through automatic schema discovery. You don't write glue code or map APIs manually because the SDK parses the MCP Server capabilities on startup. Once connected, specialized agents hand off tasks to each other to match candidates to open roles. One agent reads jobs, another calls `list_applicants` to find matches, and a third updates the status.

Track Real-Time Hiring Events

The `list_webhooks` tool lets your agent monitor system events and trigger actions when a candidate applies. This keeps your external databases synced with your hiring pipeline without polling the API. Your agent uses this event stream to trigger custom onboarding or schedule interviews. The SDK handles the connection protocol, leaving you to focus on the business logic of your hiring workflow.

Setup guide

Set up Flatwork ATS 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 Flatwork ATS tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package, define the server URL, and connect Flatwork ATS as an MCP Server in your python code. The agent automatically discovers tools like `list_jobs` and `get_applicant` with zero manual configuration.

Yes, you control this by configuring the server connection parameters or setting agent-level guardrails. This prevents the agent from running write operations like `update_application_status` when it should only read data.

The agent calls the `create_applicant` tool with a structured JSON payload containing the candidate details. The SDK validates the schema before sending it, ensuring your database remains free of corrupt formatting.

The SDK catches the error and reports the failure back to the agent. If `update_application_status` fails, the agent can retry or hand off the task to a human recruiter for manual review.

All applicant details retrieved via `get_applicant` run through an ephemeral V8 sandbox. We never store candidate resumes, names, or email addresses on our servers, ensuring your hiring data remains private.

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