How do I get a Deputy API Token?

Log in to your Deputy account, navigate to **Account Settings** → **API**, and generate a new Permanent Token for your integration.

What is the subdomain?

It is the specific URL part of your Deputy portal, for example: 'mycompany.au.deputy.com'. You need to include the full host string.

Can the agent approve timesheets?

This integration currently focuses on listing and auditing workforce data. Approving timesheets or modifying rosters should be managed through the Deputy dashboard or mobile app.

Deputy MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Deputy
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Deputy through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Deputy Assistant",
            instructions=(
                "You help users interact with Deputy. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Deputy"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Deputy MCP Server

Integrate Deputy, the ultimate workforce management solution, directly into your AI workflow. Manage your employee directory, monitor real-time shift rosters, track submitted timesheets, and handle leave requests using natural language.

The OpenAI Agents SDK auto-discovers all 10 tools from Deputy through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Deputy, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Workforce Visibility — List and retrieve detailed profiles for all employees in your Deputy organization.
Roster Monitoring — Track current and upcoming shift rosters to ensure proper coverage across locations.
Timesheet Tracking — Review submitted timesheets, including actual start and end times and approval statuses.
Leave Management — List and monitor employee leave and time-off requests pending approval.

The Deputy MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Deputy to OpenAI Agents SDK via MCP

Follow these steps to integrate the Deputy MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Deputy

Why Use OpenAI Agents SDK with the Deputy MCP Server

OpenAI Agents SDK provides unique advantages when paired with Deputy through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Deputy + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Deputy MCP Server delivers measurable value.

Automated workflows: build agents that query Deputy, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Deputy, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Deputy tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Deputy to resolve tickets, look up records, and update statuses without human intervention

Deputy MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Deputy to OpenAI Agents SDK via MCP:

get_authenticated_user

Retrieve metadata for the current authenticated API user

get_employee_profile

Get detailed information for a specific employee

list_active_rosters

List all current and upcoming shift rosters

list_business_locations

List all physical business locations (companies) configured in Deputy

list_completed_timesheets

List timesheets submitted by employees

list_currently_active_shifts

Identify employees who are currently clocked in (mock logic)

list_leave_requests

List all employee leave and time-off requests

list_pending_leave_approvals

List only the leave requests that are awaiting manager approval

list_workforce_employees

List all employees in your Deputy organization

search_employees_by_name

Search for an employee by their display name

Example Prompts for Deputy in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Deputy immediately.

"List all employees currently clocked in."

"Show me the roster for the 'Downtown Kitchen' location tomorrow."

"Are there any pending leave requests?"

Troubleshooting Deputy MCP Server with OpenAI Agents SDK

Common issues when connecting Deputy to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Deputy + OpenAI Agents SDK FAQ

Common questions about integrating Deputy MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.