How to Use the HirePOS MCP in Pydantic AI

Q: How do I configure the HirePOS MCP server inside Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your Vinkius HTTP endpoint. Pass the toolset directly to your agent configuration.

Q: Why did my Pydantic AI agent crash calling HirePOS?

The agent fails intentionally if the data from gethire or listinvoices violates your Pydantic models. Check your schema definitions against the actual API response.

Q: Is the old HTTP setup supported for Pydantic AI and the HirePOS MCP server?

No. The MCPServerHTTP class is deprecated. You must use the unified MCPToolset approach to connect to the external server.

Build strict, type-safe HirePOS rental agents using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HirePOS MCP to Pydantic AI

Create your Vinkius account to connect HirePOS 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 HirePOS with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate booking data with the MCP Server

The `list_items_by_category` tool exposes your rental catalog to Pydantic AI with strict runtime validation. When your agent calls the endpoint, the client forces the raw JSON into your defined Pydantic models. If the API returns a string where an integer should be, the framework fails loudly. You never have to worry about silent data corruption when your agent attempts to execute `create_hire` for a new contractor. Right. Let's get to it.

Audit invoices and overdue accounts

Your agent uses `list_overdue_hires` to gather late return data before financial operations run. Financial operations require precision, and this tool delivers exactly the fields you need. It then calls `get_invoice` to pull the exact penalty fees. Because Pydantic AI is model-agnostic, you can swap between Anthropic and local models to analyze this billing data without rewriting your tool logic.

Manage customer records safely

The agent runs `get_customer` to retrieve contact info and rental history with exact schemas. Handling user data means you need absolute certainty about the payload structure. Creating a new profile works the same way. The agent gathers the required fields, validates them against your Pydantic schema, and fires `create_customer`. Bad inputs get rejected before they ever reach the database.

Setup guide

Set up HirePOS 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": {
        "hirepos-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent HirePOS 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 HirePOS. 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 HirePOS 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 HirePOS MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your Vinkius HTTP endpoint. Pass the toolset directly to your agent configuration.

The agent fails intentionally if the data from `get_hire` or `list_invoices` violates your Pydantic models. Check your schema definitions against the actual API response.

Yes. Pydantic AI is model-agnostic. You can run a local open-weights model to process `check_item_availability` requests if you want to avoid cloud LLM costs.

No. The `MCPServerHTTP` class is deprecated. You must use the unified `MCPToolset` approach to connect to the external server.

The server handles sensitive financial records like line items, tax totals, and customer IDs via `get_invoice`. Vinkius routes this traffic through an ephemeral sandbox. The connection terminates instantly, leaving zero residual data behind.

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