How to Use the Buddy Punch MCP in Mastra AI

Q: How do I register the Buddy Punch tools in Mastra AI?

Instantiate the MCPClient pointing to your Vinkius server URL and spread the results of listTools() into your Mastra agent configuration. The client automatically handles SSE transport options.

Q: Can I require manual approval for Buddy Punch actions in Mastra AI?

Yes, you can configure Mastra's requireToolApproval setting on critical tools like punchinout or createemployee so a manager must approve the action in your app before it runs.

Q: Does Mastra AI support conditional branching with the Buddy Punch MCP Server?

Absolutely, you can build workflows that check listtimeentries and branch into different steps depending on whether an employee has exceeded their scheduled hours.

Build resilient, automated timesheet workflows with Mastra AI and the Buddy Punch 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 Buddy Punch MCP to Mastra AI

Create your Vinkius account to connect Buddy Punch 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 Buddy Punch with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated schedule checking and worker creation

The `create_employee` and `list_work_schedules` tools enable your Mastra AI agents to onboard new hires and assign them to active shifts. Your workflow can check if a schedule has open slots and automatically provision the employee profile in one run. Mastra handles the multi-step execution, ensuring that if the schedule lookup fails, the agent retries with exponential backoff before attempting to write the new user record.

Multi-step payroll validation with Mastra AI

The `list_pay_periods` and `list_time_entries` tools let your system audit timesheets against active payroll cycles. Mastra agents can run automated checks at the end of every week to flag missing punches before payroll runs. You write conditional branching logic to handle anomalies. For example, if an employee has unclosed punches, the agent triggers a slack notification to the manager instead of exporting bad data.

Resilient punch-in workflows with Mastra AI

The `punch_in_out` tool executes raw clock actions for workers based on external triggers like geofences or terminal taps. Mastra ensures these critical events execute reliably by managing network retries automatically. This setup uses the MCP Server to talk directly to the hardware terminal APIs. You write the logic once in TypeScript, and the system handles the physical clock-in state safely.

Setup guide

Set up Buddy Punch 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 Buddy Punch 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: "buddy-punch-mcp-client",
  servers: {
    "buddy-punch-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Buddy Punch 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 Buddy Punch. 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 Buddy Punch 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 Buddy Punch MCP in Mastra AI

Instantiate the `MCPClient` pointing to your Vinkius server URL and spread the results of `listTools()` into your Mastra agent configuration. The client automatically handles SSE transport options.

Yes, you can configure Mastra's `requireToolApproval` setting on critical tools like `punch_in_out` or `create_employee` so a manager must approve the action in your app before it runs.

Absolutely, you can build workflows that check `list_time_entries` and branch into different steps depending on whether an employee has exceeded their scheduled hours.

Mastra's built-in retry engine handles rate limits by backing off and retrying the request. This keeps your background payroll checks running without crashing the entire MCP workflow.

Your Buddy Punch API keys are encrypted at rest and injected only during runtime execution inside an ephemeral sandbox. No employee identity data or punch logs are ever persisted on our platform.

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