How to Use the WebHR MCP in Google ADK

Q: Can I check job openings and candidate pools with WebHR via Google ADK?

Yep. You call listjobpostings for what’s public, and then you use listjobcandidates to see who has applied. The agent holds both lists in its context window for combined analysis.

Q: What leave data can I pull from WebHR using the Google ADK?

The server gives you two views: listavailableleavetypes for policy, and listleaverequests for history. The long context window helps Gemini models analyze patterns across both datasets.

Q: Does the Google ADK handle multiple company departments in WebHR?

Yes. You can list all available departments using listcompanydepartments, and then use that departmental ID to filter employee details when calling getemployeedetails. It's built for structured data.

Q: If I want a comprehensive view of attendance, what WebHR tools work with Google ADK?

You start by getting the summary via getattendancesummary, and then if you need granular detail, agents pull specific logs using listattendancelogs. This sequence is ideal for BigQuery loading.

Build enterprise HR systems with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WebHR MCP to Google ADK

Create your Vinkius account to connect WebHR 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 WebHR with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process workforce attendance records.

Agents can pull aggregated metrics using `get_attendance_summary`. This data is ready to be linked directly to BigQuery for deeper analysis. Need raw clock-in/out data? Just use `list_attendance_logs`. The Google ADK's long context reasoning means it can hold these complex time series records while also accessing company departments via `list_company_departments`.

Manage personnel and organizational structure.

You can pull detailed employee profiles with `get_employee_details`. This is perfect for agents that need to cross-reference data across different Google Cloud sources. For broader views, the server lets you list all current employees (`list_employees`) or check office locations using `list_office_locations`. It supports full enterprise mapping.

Handle recruitment and internal moves.

When managing talent, agents pull open roles with `list_job_postings` and also track internal needs via `list_job_requests`. These tools work together to keep the hiring funnel accurate. Additionally, you can check out job applicants using `list_job_candidates`, keeping all your sourcing data within the Google ADK ecosystem.

Setup guide

Set up WebHR 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 WebHR 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="WebHR_agent",
    model="gemini-2.0-flash",
    instruction="You have access to WebHR 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 WebHR. 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 WebHR 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 WebHR MCP in Google ADK

The setup is simple: you pass the toolset to an LlmAgent. Because it’s built for enterprise use, all the data pulled from WebHR can be reasoned over using Gemini models and linked to BigQuery.

Yep. You call `list_job_postings` for what’s public, and then you use `list_job_candidates` to see who has applied. The agent holds both lists in its context window for combined analysis.

The server gives you two views: `list_available_leave_types` for policy, and `list_leave_requests` for history. The long context window helps Gemini models analyze patterns across both datasets.

Yes. You can list all available departments using `list_company_departments`, and then use that departmental ID to filter employee details when calling `get_employee_details`. It's built for structured data.

You start by getting the summary via `get_attendance_summary`, and then if you need granular detail, agents pull specific logs using `list_attendance_logs`. This sequence is ideal for BigQuery loading.

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