How to Use the Greenhouse MCP in LangChain

Q: How does LangChain use Greenhouse tool outputs in a chain?

The output of one tool, like getcandidatedetails, feeds directly into the next step of your LangChain run. For example, your agent reads candidate info and immediately calls updatecandidate to append evaluation notes.

Q: Can I filter candidates by department using this integration?

Use listdepartments alongside listcandidates to map applicants to specific business units. Your agent handles the cross-referencing in memory to keep your teams aligned.

Run multi-stage recruitment pipelines using LangChain to filter, move, and manage candidate data automatically using this MCP Server.

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

Build Multi-Step Recruitment Chains

The `list_open_jobs` tool pulls active Greenhouse roles directly into your LangChain run, letting your agent match incoming resumes to open seats without manual intervention. Your LangChain agent evaluates the candidate's background against the Greenhouse job metadata returned by `get_job_details` to decide if they fit. Once matched, the LangChain chain triggers `create_candidate` to build the Greenhouse profile and maps them to the right pipeline stage. This removes the manual data entry bottleneck, letting you chain Greenhouse candidate creation directly to your intake forms using LangChain.

Automate Candidate Decisions with LangChain

The `advance_application` tool moves Greenhouse candidates who pass your technical criteria to the next interview stage within your LangChain run. Your LangChain agent evaluates test scores or screening notes, then immediately updates their status in the Greenhouse pipeline. If a candidate fails to meet core requirements, the LangChain agent calls `reject_application` with a specific Greenhouse reason ID. This keeps your Greenhouse pipeline clean and ensures fast feedback loops within your LangChain workflows.

Track Pipeline Health via LangChain MCP Server

The `get_api_status` tool verifies your connection to the Greenhouse recruiting platform before running complex, multi-candidate LangChain runs. This prevents API failures halfway through a batch update of candidate records. Your LangChain agent uses `list_applications` to audit active Greenhouse roles and spot bottlenecks in your hiring stages. You get full visibility into where Greenhouse candidates are stuck by feeding this raw API data directly into LangChain's tracing tools.

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-alternative-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

Use the MultiServerMCPClient to pull the tools into your agent's execution loop using the LangChain MCP adapter. Pass the tool list directly to your agent constructor so it can run `list_candidates` and match them to roles.

Yes. Your LangChain agent analyzes scorecard data and calls `reject_application` with the required reason ID. This automates the initial screening phase based on your specific criteria.

The output of one tool, like `get_candidate_details`, feeds directly into the next step of your LangChain run. For example, your agent reads candidate info and immediately calls `update_candidate` to append evaluation notes.

Use `list_departments` alongside `list_candidates` to map applicants to specific business units. Your agent handles the cross-referencing in memory to keep your teams aligned.

Vinkius runs this MCP Server in an isolated sandbox, meaning candidate names and application histories never persist on our servers. Your API tokens remain encrypted, and data only passes directly to your LangChain runtime.

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