How to Use the MyHR MCP in LangChain

Q: How does the agent know which office or department to assign?

The agent calls listoffices and listdepartments first to get valid system IDs. It then uses those IDs to populate the payload for createemployee. This prevents bad database writes and keeps your organizational structure clean.

Run multi-step HR workflows and trace every compliance check in LangChain with this dedicated 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 MyHR MCP to LangChain

Create your Vinkius account to connect MyHR 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 MyHR with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate employee onboarding inside LangChain chains

The `create_employee` tool handles the heavy lifting of adding new hires directly into your regional database. You configure your chain to collect details, map them to the correct structural options using `list_offices` or `list_gender_options`, and commit the record without touching a web UI. It cuts out manual data entry completely. LangChain coordinates these steps sequentially. If the initial employee creation succeeds, the chain immediately triggers `create_absence_request` to log their pre-approved onboarding leave. You get a clear, step-by-step execution path that you can monitor through LangSmith to catch validation errors before they hit your database.

Audit timesheets with LangChain agents

The `list_timesheets` tool exposes active working hours directly to your decision-making agents. Your agent pulls raw logs and runs automated checks against local AU/NZ labor rules to flag anomalies. It replaces the tedious manual review process that usually eats up your Friday afternoons. Using this MCP Server, the agent analyzes hours and queries `get_employee_details` to verify department-specific pay rates. The setup runs entirely within your existing Python or TypeScript runtime. You maintain full oversight of the decision logic while the agent does the grunt work.

Track compliance across regional offices

The `list_absences` tool provides immediate visibility into scheduled time off across your entire workforce. Your LangChain agent queries this endpoint alongside `list_departments` to map staffing gaps in real time. It ensures you always have enough coverage on the floor without violating local labor standards. This integration handles the complex logic of matching absence requests to regional policies. By routing the output of `list_employees` directly into your compliance chains, you catch scheduling conflicts early. The system keeps your operations running smoothly while keeping your legal team happy.

Setup guide

Set up MyHR 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 MyHR 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({
    "myhr-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 MyHR 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 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 LangChain

You build validation steps directly into your LangChain runnables. Use `list_timesheets` to pull hours, then pass those numbers to a compliance chain that checks them against Fair Work Act rules. If something looks off, the chain flags it before payroll runs.

Yes, you track every single tool call using LangSmith. When your agent calls `create_employee` or `list_absences`, you see the exact payload, execution latency, and response code. It makes debugging API timeouts or schema mismatches incredibly straightforward.

Install the MCP adapter package and initialize the client using the Vinkius endpoint. From there, call the tool getter and pass the array to your agent. The setup takes about five minutes and gives your model direct access to all ten endpoints.

The agent calls `list_offices` and `list_departments` first to get valid system IDs. It then uses those IDs to populate the payload for `create_employee`. This prevents bad database writes and keeps your organizational structure clean.

This integration processes sensitive timesheets and employee details within a zero-trust V8 sandbox. Vinkius executes these calls ephemerally, meaning no personal information is stored on intermediate servers. Your HR data moves directly between your agent and the secure API.

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