How to Use the Greenhouse MCP in AutoGen

Q: Can AutoGen agents create new candidate profiles in Greenhouse?

Yes, an agent invokes createcandidate once your agent group agrees that a sourced profile meets your job requirements. This automates the transition from sourcing to active pipeline.

Build multi-agent networks in AutoGen that debate candidate qualifications and audit Greenhouse job structures.

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 AutoGen

Create your Vinkius account to connect Greenhouse to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Screen candidate profiles via multi-agent debate

`get_candidate` retrieves the full profile of an applicant so your AutoGen agents can analyze their qualifications. One agent can evaluate technical alignment while another checks role requirements, debating the candidate's fit before making a decision. This consensus-driven AutoGen model reduces bias during Greenhouse candidate screening. The agents exchange messages, reference the candidate details, and output a structured recommendation back to your team.

Automated pipeline auditing with AutoGen

`list_applications` pulls active submissions for your auditing agents to review. A compliance agent can use `get_application` to check if candidates are moving through the correct hiring stages without skipping mandatory steps. If the AutoGen compliance agent flags an issue, it coordinates with other agents to rectify the Greenhouse record. You build a self-correcting system that keeps your ATS clean and organized.

Coordinate job openings across teams

`list_jobs` allows your hiring agents to track open positions across the company. They cross-reference this with `list_users` to match hiring managers with their active roles, ensuring no vacancy goes unmanaged. This keeps your AutoGen recruiting team aligned on Greenhouse vacancies without manual check-ins. The Greenhouse MCP server provides the ground truth that your agent network needs to coordinate tasks.

Setup guide

Set up Greenhouse MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Greenhouse tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Greenhouse_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Greenhouse data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Greenhouse_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Greenhouse data")
    print(result.messages[-1].content)

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 AutoGen

Use the MCP adapter from the extensions package to load the tools. Pass the resulting list directly to your AssistantAgent constructor to begin multi-agent execution.

Yes, an agent invokes `create_candidate` once your agent group agrees that a sourced profile meets your job requirements. This automates the transition from sourcing to active pipeline.

The agents schedule tool calls sequentially within their conversation loop, preventing simultaneous bursts of requests to the MCP server that could trigger API rate limiting.

Yes, you can combine this MCP server with others. This lets your agents pull candidate info from Greenhouse and coordinate responses with internal communication systems.

The MCP server runs inside an isolated V8 sandbox that handles authentication securely. Your Greenhouse user lists and hiring metrics are never exposed to external servers or stored long-term, maintaining strict operational security.

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