How to Use the KeyPay MCP in Pydantic AI

Use Pydantic AI with KeyPay for type-safe payroll automation that fails loudly on unexpected API data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KeyPay MCP to Pydantic AI

Create your Vinkius account to connect KeyPay 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 KeyPay with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe KeyPay tool usage

Every response from `get_pay_run_details` or `list_employees` is validated against your Pydantic models. If the API returns malformed data, your agent stops immediately. This prevents silent errors from propagating through your payroll workflows. You get reliable data structures every time the agent invokes a tool.

Strict payroll data validation

Your agent enforces strict schemas when interacting with `list_pay_run_earnings`. It ensures that every salary figure and deduction matches your expected types. It brings sanity to your integration. You define the model, and the MCP Server ensures the incoming payroll data complies with your standards.

Reliable employee data management

Retrieve and verify employee information using `get_employee_details` with full type safety. The agent validates the record before attempting any further processing. It eliminates the risk of hallucinated fields. Your code remains clean because you know exactly what the API returns before the agent acts.

Setup guide

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

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

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

The framework automatically maps the tool's JSON output to your Pydantic models. If the structure doesn't match, the request fails, preventing corrupt data from entering your system.

Absolutely. Because your models are typed, any missing or incorrectly formatted payroll field triggers a validation error. This makes debugging your agent's interactions much easier.

You can define models that match the specific KeyPay responses you need. By using the provided toolset, you get a solid foundation for building your typed payroll agent.

You run the server externally and connect via HTTP. Pydantic AI handles the transport and ensures that the communication remains consistent during the agent's task.

Your agent only processes the specific payroll records requested. Since you define the validation models, you control exactly which pieces of employee data are parsed and kept in memory.

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