How to Use the MyHR MCP in Pydantic AI

Build strictly typed HR agents with Pydantic AI that validate every AU/NZ timesheet and leave request at runtime.

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 Pydantic AI

Create your Vinkius account to connect MyHR to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe HR with Pydantic AI

The `get_employee_details` tool returns structured profiles that your agent validates instantly. If the API drops a required field like a tax identifier, your Pydantic model throws a validation error and halts the run. This prevents silent data corruption. Your agent never attempts to process a malformed AU/NZ employee record because the framework enforces the schema before the next step executes.

Enforce strict timesheet schemas

The `list_timesheets` tool expects specific date formats and decimal hours when you query it. You define the exact Pydantic schema for these records to match your backend payroll system. The framework catches type mismatches immediately. If an employee logs a string instead of an integer for their hours, the agent fails loudly rather than passing bad math to your accounting software.

Execute validated MCP Server operations

The `create_employee` tool requires precise payloads to generate a valid profile. Your agent gathers required data from `list_gender_options` and `list_marital_statuses` to build that payload. Because Pydantic AI is model-agnostic, you swap between Anthropic and OpenAI without rewriting your validation logic. The agent always submits the exact JSON structure the MyHR backend demands.

Setup guide

Set up MyHR MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "myhr-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to MyHR tools.",
)

result = await agent.run("List recent MyHR transactions")
print(result.output)

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 Pydantic AI

Install the slim package with the MCP extra. Create an MCPToolset with your Vinkius HTTP URL and attach it to your Agent's toolsets array.

Yes. The framework converts the MCP Server tool definitions into strict Pydantic models. It validates all inputs and outputs at runtime.

HR data requires absolute correctness. If an agent hallucinates a department ID when creating an absence request, Pydantic catches the invalid type before the API call fires.

Use Streamable HTTP. The older HTTP implementation is deprecated in Pydantic AI, so stick to the unified MCPToolset approach for this MCP connection.

No. Vinkius routes the leave dates and medical notes directly from the API to your Python runtime. The ephemeral sandbox shuts down immediately after the response, leaving no trace of the request.

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