How to Use the CATS ATS MCP in OpenAI Agents SDK

Q: How do I connect CATS ATS to OpenAI Agents SDK?

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Vinkius endpoint URL. Pass it to your agent using the mcpservers parameter.

Q: Can OpenAI Agents SDK cache CATS ATS candidate searches?

Yes. Set cacheToolsList=True in your server configuration. This prevents the agent from re-fetching the tool schemas every time it wants to search candidates.

Connect CATS ATS to your OpenAI Agents SDK system. Build production recruitment agents with strict guardrails and full execution tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CATS ATS MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse resumes and match jobs with OpenAI Agents SDK

Your multi-agent system needs access to real applicant data, not mockups. Dropping the CATS ATS MCP Server into your configuration exposes live recruitment records instantly. The primary agent can run `search_candidates` to find specific skill matches while a specialized compliance agent checks the output. Handoffs work perfectly here. One agent queries `list_job_orders` to find open reqs, then transfers control to a sourcing agent that pulls detailed histories using `get_candidate_details`. OpenAI's tracing dashboard logs every single API call, so you know exactly which records your agents touched.

Track recruiter actions safely

Production systems require strict boundaries. You do not want a rogue agent hallucinating interview notes. By setting up explicit guardrails in your OpenAI MCP Server configuration, you control exactly how your system interacts with `list_recruitment_activities`. The agents read the exact notes left by human recruiters. They pull contact data via `list_recruitment_contacts` and summarize recent touchpoints. If an agent tries to invent a missing phone number, the guardrails catch it before the user ever sees the output.

Map client companies automatically

Agency recruiters juggle dozens of client accounts. Your custom agent can map these relationships by calling `list_recruitment_companies` directly from the ATS database. It pulls the raw firmographic data into the agent's context window. Because you pass the server directly to the Agent constructor, tool discovery happens without writing custom wrappers. The system immediately knows how to fetch specific role requirements using `get_job_details` and bind them to the correct client profile.

Setup guide

Set up CATS 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 CATS ATS tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CATS 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 CATS 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="CATS ATS Agent",
            instructions="You have access to CATS 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 CATS 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 CATS 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 CATS ATS MCP in OpenAI Agents SDK

Install `openai-agents` via pip. Initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass it to your agent using the `mcp_servers` parameter.

Yes. Set `cacheToolsList=True` in your server configuration. This prevents the agent from re-fetching the tool schemas every time it wants to search candidates.

It works flawlessly. You can restrict the ATS tools to a specific sourcing agent. When your main routing agent needs applicant data, it simply hands off the task.

Check your OpenAI tracing dashboard. Every time an agent triggers `get_job_details`, the exact request payload and ATS response appear in your execution logs.

Vinkius runs the integration in an isolated V8 sandbox. The system only reads resumes, notes, and contact info when explicitly commanded. Tokens are ephemeral, and data passes straight to your environment without resting on our servers.

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