How to Use the Ninehire MCP in OpenAI Agents SDK

Build production-grade hiring agents on the OpenAI Agents SDK that manage your entire Ninehire recruiting pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ninehire MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Applicant Screening

Let one agent find jobs and another screen the candidates. Your sourcing agent can call `list_job_postings` to find relevant openings, then hand off to a screening agent that uses `list_job_applicants` for that specific role. The screening agent then pulls each profile with `get_applicant_profile` and reviews past feedback using `list_candidate_evaluations`. The OpenAI SDK's built-in guardrails mean you can trace every step and prevent agents from taking unapproved actions.

Manage Your Ninehire MCP Server

Your agent can manage its own setup. It starts by running `check_api_health` to make sure Ninehire is responding. It can also pull its own account details with `get_authenticated_user_info` to confirm permissions. For more complex workflows, the agent can inspect `list_configured_webhooks` to understand how Ninehire is sending data to other systems. This isn't just about running tasks; it's about building agents that are aware of their environment.

Structure Your Hiring Process

Map your company's structure directly into your agent's logic. Start by fetching your company layout with `list_organization_departments` and `list_hiring_teams`. When you post a new job, the agent can use `get_job_details` to see which team it belongs to and ensure applicants are routed correctly. It's how you move from simple commands to a system that actually understands your org chart.

Setup guide

Set up Ninehire 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 Ninehire tools at runtime.
3

Create your Agent

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

Run the agent

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

It's automatic. Once you connect the Ninehire MCP server, the OpenAI Agents SDK introspects the available tools and makes them available to your agent. You don't need to manually define functions for `get_applicant_profile` or `list_job_postings`.

Yes, that's what it's designed for. You can have one agent for sourcing candidates via `list_job_postings` and another for screening them with `list_candidate_evaluations`. The SDK handles the handoff between them.

Yes. The SDK includes guardrails that let you review and approve agent actions before they're executed. You get full control and a complete trace of what the agent is doing in your Ninehire account.

Your agent can handle it. A good practice is to have the agent call `check_api_health` before running a batch of tasks. If the API is unhealthy, the agent can pause and retry later instead of failing.

All communication is over a secure, authenticated channel. The server itself is ephemeral, and Vinkius ensures access is locked down. Your agent only touches applicant profile and evaluation data from `get_applicant_profile` as needed for a specific task.

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