How to Use the MyHR MCP in LlamaIndex

Q: Can LlamaIndex agents write data back to MyHR?

Yes, your agent can execute writes using createabsencerequest or createemployee. While RAG workflows usually read data, the tool spec exposes write capabilities so your agent can take action based on its search findings.

Q: How does MyHR handle New Zealand and Australia compliance in LlamaIndex?

The agent queries listtimesheets and compares the results against indexed local award regulations. If a timesheet shows a compliance gap, this MCP Server setup flags the specific node. This keeps your business aligned with Fair Work and Holidays Act standards.

Q: Do I need to manually map gender and marital status options?

No, the agent queries listgenderoptions and listmaritalstatuses directly. It indexes these options so it always uses valid values when building new profiles. This eliminates data validation errors during onboarding.

Index timesheets and employee records into LlamaIndex to query your regional HR data with full context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MyHR MCP to LlamaIndex

Create your Vinkius account to connect MyHR to LlamaIndex 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 MyHR with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index active staff records into LlamaIndex

The `list_employees` tool pulls your complete worker directory to build a searchable local index. LlamaIndex takes this raw data and structures it so your model can query staff details without making constant API calls. It turns a static directory into a dynamic knowledge base. You query the index using natural language to find specific profiles. The model cross-references results with `get_employee_details` to pull up-to-date contract terms on demand. It saves your team from digging through database tables when they need quick answers.

Analyze timesheet history with RAG pipelines

The `list_timesheets` tool feeds historical work hours directly into your vector store. LlamaIndex processes these records, allowing you to run semantic searches over months of payroll data. You can spot trends in overtime or identify departments that consistently run over budget. This MCP Server connects your live HR database directly to your retrieval-augmented generation pipelines. By combining timesheet data with organizational metadata from `list_departments`, your queries yield highly accurate insights. You get clear reports grounded in actual company data.

Track regional leave patterns in LlamaIndex

The `list_absences` tool retrieves all pending and past time-off requests across your organization. LlamaIndex indexes these events using the MCP protocol, making it simple to query seasonal staffing shortages or verify leave balances. Your model answers scheduling questions using real-time policy data. When a manager asks about coverage, the index checks active records against `list_offices` to verify regional holidays. It prevents scheduling conflicts before they happen. The system keeps your staffing levels aligned with local operational requirements.

Setup guide

Set up MyHR MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all MyHR MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to MyHR tools.",
)
response = await agent.run("List recent MyHR data")

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 MyHR. 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 MyHR 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 MyHR MCP in LlamaIndex

You load the data using the MCP tool spec and run a vector index pipeline. The `list_timesheets` tool fetches the raw records, which LlamaIndex converts into document nodes for semantic search. This lets you query payroll trends using natural language.

Yes, your agent can execute writes using `create_absence_request` or `create_employee`. While RAG workflows usually read data, the tool spec exposes write capabilities so your agent can take action based on its search findings.

The agent queries `list_timesheets` and compares the results against indexed local award regulations. If a timesheet shows a compliance gap, this MCP Server setup flags the specific node. This keeps your business aligned with Fair Work and Holidays Act standards.

No, the agent queries `list_gender_options` and `list_marital_statuses` directly. It indexes these options so it always uses valid values when building new profiles. This eliminates data validation errors during onboarding.

All calls to fetch absence requests and employee records run through an ephemeral V8 sandbox. Vinkius handles the underlying authentication tokens securely, ensuring your raw data is never exposed to public LLM APIs. Your local vector store remains the sole repository of indexed data.

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