How to Use the Greenhouse MCP in LangChain

Q: Can a LangChain agent write data back to Greenhouse?

Yes, the agent uses the createcandidate tool to write new profiles directly to your ATS. You only need to make sure your Vinkius credentials allow write operations for your Greenhouse organization.

Q: How does LangChain trace tool calls made to Greenhouse?

Every time your agent invokes getcandidate or listjobs, LangSmith logs the exact payload, execution speed, and token cost. This gives you complete visibility into your automated recruiting pipelines.

Build multi-step recruiting pipelines in LangChain by linking Greenhouse tools directly into your reasoning chains.

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 LangChain

Create your Vinkius account to connect Greenhouse to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step hiring chains in LangChain

`list_jobs` lets your agent find open roles before it takes any other action. Once the agent identifies the active job IDs, it passes that data directly to `create_candidate` to file new applicants in the correct pipeline without manual data entry. This chain runs sequentially, meaning the output of your job search feeds the candidate creation step. You get a transparent audit trail of your Greenhouse sourcing process inside LangSmith to track token usage and latency.

Audit applications with deep context

`list_applications` pulls recent submissions so your agent can verify who is moving through your pipeline. By extracting those application IDs, the agent runs `get_application` to pull specific details like interview notes and hiring stages. You don't have to copy-paste Greenhouse candidate IDs between different interfaces when building your LangChain workflow. The framework handles the state across these calls, letting you build custom scoring pipelines that evaluate candidates against actual job requirements.

Map organizational structures instantly

`list_departments` retrieves your company's structural layout to help categorize new roles. Combining this with `list_offices` and `list_users` lets your agent map out exactly who owns which hiring process across different physical locations. This setup eliminates the guesswork when setting up new roles. Your pipelines can assign coordinators and hiring managers automatically based on the department and office data returned by the Greenhouse MCP server.

Setup guide

Set up Greenhouse MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Greenhouse tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "greenhouse-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Greenhouse transactions"
    })
    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 LangChain

Install the adapter package and use the client pointing to your Vinkius MCP endpoint. This setup imports the 12 tools directly into your agent's toolkit with a single configuration block.

Yes, the agent uses the `create_candidate` tool to write new profiles directly to your ATS. You only need to make sure your Vinkius credentials allow write operations for your Greenhouse organization.

Every time your agent invokes `get_candidate` or `list_jobs`, LangSmith logs the exact payload, execution speed, and token cost. This gives you complete visibility into your automated recruiting pipelines.

You can mix and match. Your agent can search a database, find a resume, and then use the Greenhouse MCP server to create the candidate in one continuous loop.

Your candidate profiles and application histories are processed inside an isolated MCP sandbox. Vinkius does not store candidate names, emails, or resumes retrieved by the tools, keeping your recruiting data 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