How to Use the Greenhouse MCP in Google ADK

Q: How do I configure Greenhouse MCP tools inside Google ADK?

Use McpToolset with the HTTP transport parameters pointing to your Vinkius endpoint. Pass this toolset directly to your LlmAgent constructor to expose the Greenhouse tools.

Q: Can I limit which Greenhouse tools Google ADK can access?

Yes, you can pass an optional toolnames filter to your McpToolset initialization. This prevents Gemini from seeing or executing powerful actions like createcandidate if you only want it reading job data.

Q: Does Google ADK support real-time Greenhouse pipeline analysis?

Yes, by combining listapplications with Gemini's long-context capabilities. The agent pulls active application states and processes them alongside your internal Google Cloud recruiting metrics.

Feed Greenhouse talent pipelines directly into Gemini long-context loops using Google ADK and our 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 Google ADK

Create your Vinkius account to connect Greenhouse to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Mine talent pools with Gemini and Google ADK

The `list_candidates` tool pulls historical profiles straight into Gemini's context window. Google ADK lets you feed this raw candidate data directly into your analytical runs to find past applicants who fit new roles. Your agent calls `get_candidate` to pull deep work histories for top matches. This bypasses slow database queries by letting the model reason over the entire applicant database in a single turn.

Map Greenhouse MCP Server data to Google Cloud databases

The `list_jobs` tool provides the structural schema needed to align your live ATS with enterprise data warehouses. Your Google ADK agent pulls active job openings, then joins them with regional hiring targets stored in BigQuery. By using `list_departments` and `list_offices`, the agent maps physical locations and business units to your cloud-based financial models. You get real-time hiring velocity reports without manual export scripts.

Audit application status trends at scale

The `list_applications` tool queries your active pipelines to expose bottlenecks in your screening process. Your Google ADK agent processes these application arrays, identifying which stages hold up candidates the longest. The agent calls `get_application` on delayed profiles to extract specific recruiter notes. Because the ADK integrates with Vertex AI, you can run sentiment analysis on feedback to find systemic bias in your reviews.

Setup guide

Set up Greenhouse MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Greenhouse tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Greenhouse_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Greenhouse tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use `McpToolset` with the HTTP transport parameters pointing to your Vinkius endpoint. Pass this toolset directly to your `LlmAgent` constructor to expose the Greenhouse tools.

Yes, you can pass an optional `tool_names` filter to your `McpToolset` initialization. This prevents Gemini from seeing or executing powerful actions like `create_candidate` if you only want it reading job data.

Yes, by combining `list_applications` with Gemini's long-context capabilities. The agent pulls active application states and processes them alongside your internal Google Cloud recruiting metrics.

The connection runs through Vinkius's optimized V8 sandbox, minimizing latency. Google ADK handles the streamable HTTP responses efficiently, ensuring tools like `list_candidates` execute without timing out.

Vinkius hosts the MCP connection in a zero-trust environment, injecting your credentials at the edge. Google ADK never sees your raw Greenhouse application records, job listings, or candidate contact info; it only interacts with the secure, authenticated endpoint.

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