How to Use the Deputy MCP in Mastra AI

Q: How do I configure automatic retries for Deputy tools in Mastra AI?

Define a workflow step that calls listcompletedtimesheets and apply Mastra's built-in retry block. If the API hits a rate limit, the runner backs off exponentially before attempting the call again.

Q: Can I enforce human approval before Mastra AI modifies a Deputy roster?

Yes, you can set requireToolApproval on tools like listactiverosters within your agent definition. The workflow will pause and wait for a manual signature before executing the schedule update.

Q: Can a Mastra AI agent search employees across multiple locations?

Absolutely. The agent can first query listbusinesslocations to map your operating units, then run searchemployeesbyname across those specific location contexts to find the right staff member.

Build automated HR workflows that run Deputy actions with Mastra AI's conditional engine using our MCP Server.

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 Mastra AI

Create your Vinkius account to connect Deputy to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Timesheets with Mastra AI Workflows

The `list_completed_timesheets` tool serves as the entry point for your automated workforce auditing pipelines. You configure a Mastra AI workflow that triggers every Friday, pulls the timesheet payloads, and passes them to your agent for verification. If the agent flags an anomaly, the workflow branches to notify a supervisor instead of blindly writing data. This keeps your payroll records accurate without requiring manual daily spot checks.

Resolve Roster Gaps Using the Deputy MCP Server

The `list_active_rosters` tool allows your Mastra AI agent to scan for upcoming empty shifts and identify scheduling conflicts. When a gap is found, the agent queries `list_workforce_employees` to match qualified staff members who are not currently scheduled. You can build a multi-step workflow that drafts a replacement roster and holds it for approval. This guarantees that your business locations always have adequate shift coverage without manual scheduling headaches.

Route Leave Requests with Mastra AI Step Functions

The `list_pending_leave_approvals` tool feeds pending time-off requests into your Mastra AI routing logic. The workflow evaluates the request against active rosters using `list_leave_requests` to see if the dates conflict with peak business hours. If a conflict exists, the step function escalates the decision to a human manager via the approval mechanism. You get automated triage for standard time-off requests while keeping eyes on tricky scheduling conflicts.

Setup guide

Set up Deputy MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Deputy tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "deputy-mcp-client",
  servers: {
    "deputy-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Deputy Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Deputy tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Deputy transactions"
);
console.log(result.text);

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 Mastra AI

Define a workflow step that calls `list_completed_timesheets` and apply Mastra's built-in retry block. If the API hits a rate limit, the runner backs off exponentially before attempting the call again.

Yes, you can set `requireToolApproval` on tools like `list_active_rosters` within your agent definition. The workflow will pause and wait for a manual signature before executing the schedule update.

You initialize the client using the Vinkius HTTP URL and your secure endpoint token. The framework automatically maps the tools, enabling your agents to call `get_authenticated_user` without manual header configuration.

Absolutely. The agent can first query `list_business_locations` to map your operating units, then run `search_employees_by_name` across those specific location contexts to find the right staff member.

No, Mastra AI processes employee records and shift times in memory during execution. Your data stays within your execution environment and the secure, ephemeral Vinkius MCP sandbox.

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