Greenhouse MCP for AI. Manage the entire hiring pipeline via conversation.

Q: Can I update candidate details with updatecandidate?

Yes. You can use updatecandidate to modify specific profile information, like changing an applicant's phone number or updating their current job title in the system record.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Greenhouse MCP connects your AI agent directly to your entire recruiting pipeline. List candidates, check job openings, and move applicants through stages—all via natural conversation.

You get total control over candidate records, departmental structures, and active job postings without leaving your preferred chat environment.

What your AI can do

Advance application

Moves a candidate's application to the next stage in the pipeline.

Create candidate

Adds an entirely new person into your system with their name and company.

Get api status

Checks if the connection between your account and the MCP is working correctly.

+ 9 more capabilities included

Manage Candidate Records

Create new candidate profiles and modify existing information like contact details or current company titles.

Track Job Openings

Retrieve metadata for all active job roles, including which department owns the opening and who the hiring team is.

Audit Application Statuses

List all submitted applications or get detailed information on a specific candidate's journey through the hiring pipeline.

Identify Company Structure

Retrieve complete lists of company departments and office locations to coordinate global recruitment efforts.

Workflow Actioning

Move an applicant instantly, advancing them to the next interview stage or formally rejecting their application with a required reason.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Greenhouse: 12 Tools for Recruiting Ops

These tools allow you to automate key functions across the entire hiring lifecycle, from listing open jobs to advancing candidate records.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Greenhouse on Vinkius

Advance Application

Moves a candidate's application to the next stage in the pipeline.

Create Candidate

Adds an entirely new person into your system with their name and company.

Get Api Status

Checks if the connection between your account and the MCP is working correctly.

Get Candidate Details

Pulls up all existing information about a specific candidate record.

Get Job Details

Retrieves deep metadata for any single, active job opening.

List Applications

Generates a list of all submitted job applications for review.

List Candidates

Provides an inventory of every candidate currently in the system.

List Departments

Lists all existing departments within your company structure.

List Open Jobs

Shows all currently active and open job postings across the company.

List Offices

Retrieves a list of physical office locations.

Reject Application

Marks a candidate's application as rejected, requiring you to specify a reason code.

Update Candidate

Modifies specific data points for an existing candidate profile.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Greenhouse integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "greenhouse-alternative": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Greenhouse tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"greenhouse-alternative": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Greenhouse, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

The Struggle of Status Checks

Right now, checking a candidate's progress feels like detective work. You open your ATS and find the job ID; then you have to check which department owns it, cross-reference that with an office location sheet, and finally click through several pages just to see if they were advanced or rejected.

With this MCP connection, all of that complexity disappears. Your agent handles the lookups for department lists, open jobs, and candidate records in one shot. You don't navigate; you talk. It’s faster, cleaner, and it keeps your workflow focused on people, not clicks.

Using Greenhouse with AI

The most tedious parts of the job vanish: manually pulling a candidate's full history from multiple sources, or having to update their company name in three different places. Your agent performs these updates and data pulls automatically via `update_candidate` or `get_candidate_details`.

Your AI client becomes your dedicated HR assistant. You get an immediate, accurate answer—you don't wait for a junior analyst to run the report. That’s the difference.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

This MCP lets you treat your Applicant Tracking System like a conversational partner. Instead of clicking through dozens of tabs to find out where a candidate stands, you just ask your agent. Need to know which departments exist? Ask. Need to check if the API is working right now? Just ask.

Your AI client handles the heavy lifting: listing all active job openings or finding a specific candidate's full history, including their contact details and professional titles. Everything flows through this single point of access on Vinkius. It turns complex HR operations into simple dialogue.

Your agent acts as your dedicated coordinator. You can manage applications by advancing top talent to the next interview stage or marking records as rejected with specific reasons. This eliminates manual data entry, letting you focus entirely on hiring people.

Built · Hosted · Managed by Vinkius Greenhouse MCP - Manage Candidate Data with AI

Server ID 019dd0fd-ea39-722d-9e0c-fe7cb5a923bd

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

You instantly know who's in the system. Use list_candidates or list_applications to pull full lists, giving you a complete view of your talent pool at a glance.

Keep track of every single job opening without leaving your chat. Call list_open_jobs and get detailed metadata for any role using get_job_details.

Update candidate information quickly. If John Smith changes his employer, just run update_candidate instead of logging into the web portal.

Control the workflow directly. Use advance_application to move a promising applicant right to the next stage or call reject_application when necessary.

Coordinate logistics effortlessly. Need to know if you have an office in Berlin? Run list_offices. Want to see which department owns that role? Call list_departments.

See it in action

01 01

Need to update a candidate's company name.

A recruiter finds an old record for Jane Doe and needs her current employer listed. Instead of manually finding the profile, they ask their agent to run update_candidate on Jane Doe's ID with the new company name.

02 02

Reviewing all jobs in a specific area.

A hiring manager needs to see every open role within 'Engineering'. They prompt the agent using list_open_jobs, which immediately returns all relevant job titles and IDs for review.

03 03

Closing out a stalled application.

An applicant hasn't responded in weeks. The recruiter asks to run reject_application on the specific ID, ensuring that the rejection is logged with an official reason code before closing the record.

04 04

Initial data gathering for a new hire.

A hiring manager wants to know what resources are available. They ask their agent to run list_departments and list_offices simultaneously, getting all structural data needed for the job description.

The honest tradeoffs

Guessing a candidate's current status

Anti-pattern

The user just asks, 'What is this candidate doing?' and gets no helpful response.

The Fix

Instead, ask your agent to run get_candidate_details or use the list_applications tool. These calls retrieve precise data about their stage in the pipeline.

Trying to list all candidate info at once

Anti-pattern

The user attempts a single, vague query like 'give me everything on John Smith'.

The Fix

Be specific. Use get_candidate_details for the full profile or use list_candidates if you need an inventory to start with.

Ignoring job department details

Anti-pattern

The user only sees a job title, but doesn't know which internal team owns it.

The Fix

Run get_job_details for that specific job ID. This provides the necessary metadata, including the owning department and hiring teams.

When It Fits, When It Doesn't

Use this MCP if your process relies on querying state—that is, when you need to know what status something currently has (e.g., Is John Doe active? What are our open jobs?). This tool suite excels at data retrieval and workflow actioning, like using advance_application or update_candidate. Do not use this if your primary task is generating complex, creative content (like writing job descriptions from scratch); for that, a general AI agent is better. However, never rely on external spreadsheets for core records; always check the system status first by running get_api_status to ensure data integrity.

Questions you might have

How do I list all my current job openings using list_open_jobs? +

Simply tell your agent, 'List all open jobs.' The tool runs list_open_jobs and returns a comprehensive list of every active role available for hiring.

Can I update candidate details with update_candidate? +

Yes. You can use update_candidate to modify specific profile information, like changing an applicant's phone number or updating their current job title in the system record.

What is the best way to move a candidate forward using advance_application? +

You tell your agent which application ID needs advancing. The tool executes advance_application, and the candidate's status immediately updates within Greenhouse.

Why do I need get_api_status? +

It checks the connection between this MCP and your Greenhouse account. Running get_api_status ensures that any command you send to your agent will actually execute correctly.

How do I use `create_candidate` when I find a promising lead outside of Greenhouse? +

It adds a new candidate record right away. You just need to provide their first name, last name, and company affiliation for the tool to create the profile successfully.

What details does `reject_application` require to process an application rejection? +

It requires a specific reason ID. Providing this ensures that every rejected application is properly documented within Greenhouse's system, which is key for auditing and tracking trends.

How can I get comprehensive data about one person using `get_candidate_details`? +

It pulls all available records tied to a single individual. This lets you review their complete history and current status without having to manually search through the entire ATS.

If I need a summary of recent submissions, how do I use `list_applications`? +

This tool pulls a list of job applications across various roles. It's great for getting an immediate overview of who applied and which specific positions they were interested in.

What is the 'On-Behalf-Of' requirement? +

Greenhouse requires write operations to be associated with a specific User ID for auditing. This ID is passed in the header to identify who performed the action.

Can I search for candidates by email? +

Yes! Use the list_candidates tool and provide the email parameter to find a specific person's recruitment record and history.

How do I advance an application to the next stage? +

The advance_application tool requires a valid application ID. It will automatically move the candidate to the next sequential stage defined in your job's workflow.

Connect to your AI in seconds.

Advance application

Create candidate

Get api status

Greenhouse: 12 Tools for Recruiting Ops

Make your AI actually useful.

Advance Application

Create Candidate

Get Api Status

Get Candidate Details

Get Job Details

List Applications

List Candidates

List Departments

List Open Jobs

List Offices

Reject Application

Update Candidate

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

The Struggle of Status Checks

Using Greenhouse with AI

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Need to update a candidate's company name.

Reviewing all jobs in a specific area.

Closing out a stalled application.

Initial data gathering for a new hire.

The honest tradeoffs

Guessing a candidate's current status

Trying to list all candidate info at once

Ignoring job department details

When It Fits, When It Doesn't

Questions you might have