How to Use the Greenhouse MCP in OpenAI Agents SDK

Q: How do I connect the Greenhouse MCP Server to the OpenAI Agents SDK?

Install the package with pip install openai-agents and set up the streamable HTTP server. You pass the server instance using MCPServerStreamableHttp into your Agent constructor. Setting cacheToolsList=True ensures fast execution.

Q: How do I check if my API connection to the Greenhouse server is active?

Run the getapistatus tool through your agent to verify connectivity. It returns the current status of your Greenhouse API integration. This is useful for health checks in production environments.

Build reliable hiring workflows with the Greenhouse MCP Server and OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Greenhouse MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fast track candidates with OpenAI Agents SDK

The `advance_application` tool moves qualified candidates to the next stage of your hiring pipeline instantly. You do not have to click through the Greenhouse dashboard to keep things moving. If a candidate does not fit, the `reject_application` tool handles the rejection clean and fast with a required reason ID. Your agents can filter out bad fits before a human recruiter even looks at the queue, keeping the hiring pipeline clean.

Map roles using the Greenhouse MCP Server

The `list_open_jobs` tool pulls active roles straight into your OpenAI agent context. This lets your agent match incoming candidate resumes against actual open positions without manual lookup. Combine this with `list_departments` and `list_offices` to route applications to the correct hiring manager. Your agent handles the organizational mapping behind the scenes, ensuring candidate profiles land in the right inbox.

Build profiles inside OpenAI Agents SDK

The `create_candidate` tool lets your agent log new applicants directly into your database. It handles first names, last names, and company data to build clean profiles without human data entry. Once created, you can run `update_candidate` to modify details as the interview progresses. Your production agent system keeps candidate records fresh and accurate, updating everything in real time.

Setup guide

Set up Greenhouse 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 Greenhouse tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package with `pip install openai-agents` and set up the streamable HTTP server. You pass the server instance using `MCPServerStreamableHttp` into your Agent constructor. Setting `cacheToolsList=True` ensures fast execution.

Yes, you can build strict guardrails into your agent to validate actions before they run. Use the `advance_application` tool to move candidates forward only when specific scorecard criteria are met. This prevents accidental stage transitions in your pipeline.

Tools are auto-discovered when you pass the server parameter to the agent. The SDK queries the MCP Server to find tools automatically. No manual schema mapping is required.

Run the `get_api_status` tool through your agent to verify connectivity. It returns the current status of your Greenhouse API integration. This is useful for health checks in production environments.

All candidate personal details and application records are processed inside an ephemeral V8 sandbox. Vinkius handles the authorization token securely, meaning your raw Greenhouse API keys are never exposed to the LLM. Data is wiped as soon as the execution finishes.

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