How to Use the Deputy MCP in Pydantic AI

Use Deputy with Pydantic AI to enforce type safety on every shift and leave request your agent processes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deputy MCP to Pydantic AI

Create your Vinkius account to connect Deputy 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 Deputy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe roster management for Pydantic AI

Every response from `list_active_rosters` is validated against Pydantic models. You get clean, typed data instead of raw JSON blobs. If the API schema shifts, your agent catches it immediately. You avoid runtime crashes caused by unexpected field formats.

Validating leave requests in Pydantic AI

Your agent uses `list_leave_requests` to pull time-off data into your Python workflow. The validation layer checks every field before it hits your logic. This guarantees that dates and employee IDs match your expected format. You build complex scheduling rules with absolute confidence.

Fetching workforce lists for Pydantic AI agents

Retrieve your entire organization list with `list_workforce_employees`. The agent maps these results into structured Python objects for easier processing. It handles the heavy lifting of parsing the API response. You focus on writing the business logic that uses the employee data.

Setup guide

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

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

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

Initialize the MCPToolset with your server URL and pass it to your Agent. Pydantic AI handles the type validation for all incoming tool data.

The agent throws a validation error immediately. This prevents the system from acting on hallucinated or malformed employee records.

Yes, the server is model-agnostic. Pydantic AI works with any model you choose, provided the server is reachable via HTTP.

Vinkius hosts the server in an ephemeral sandbox. Your API keys are managed centrally, and the agent only interacts with the server through a secure, tokenized connection.

It processes timesheet logs, leave requests, and employee roster slots. Each payload is encrypted in transit and validated on arrival to ensure data integrity.

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