How to Use the Homebase MCP in Mastra AI

Q: How do I register the Homebase MCP Server in Mastra AI?

Install the package using npm install @mastra/mcp@latest. Create a new MCPClient instance pointing to your server URL, then spread mcpClient.listTools() directly into your Mastra AI agent configuration.

Q: Can I require manager approval before Mastra AI pulls Homebase timecards?

Yes, you can configure requireToolApproval for sensitive endpoints like listtimecards. This pauses Mastra execution and prompts a manager to review the action before the agent accesses actual hours worked.

Q: How does Mastra AI resolve the Homebase location UUID?

The Mastra workflow engine runs listlocations as an initial step to find the correct locationuuid. It then stores this ID in context, feeding it into subsequent tools like listdepartments or listemployees.

Build resilient, self-healing workforce workflows with the Homebase MCP Server and Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Homebase MCP to Mastra AI

Create your Vinkius account to connect Homebase 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 Homebase with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Homebase Schedule Audits in Mastra AI

The `list_labor_budgets` tool lets you build Mastra AI workflows that automatically run when Homebase labor costs spike. The Mastra agent checks your current spending limits against actual hours worked. If the budget is exceeded, Mastra triggers a branch to alert managers. By combining `list_scheduled_shifts` with your custom Mastra rules, you can catch Homebase scheduling errors before they hit payroll. The Mastra workflow engine handles the logic, while the agent pulls the data.

Handle API Flakes with Automatic Retries

When querying `list_timecards`, Mastra automatically retries failed Homebase requests using exponential backoff. This ensures your automated Mastra payroll scripts get the data they need even during peak hours. Your Mastra AI agents can safely pull `get_active_clock_ins` and match them against Homebase schedules. If the Homebase API rate limit is reached, the Mastra client pauses and retries without failing the entire run.

Human-in-the-Loop Approvals for Staffing Changes

Prevent unauthorized changes to employee profiles by requiring approval before calling `get_employee_profile` through the Mastra MCP server. Use Mastra's tool approval to pause the workflow when the agent attempts to modify Homebase data. A manager must click approve before the agent can view the profile. This keeps your compliance teams happy while still automating the boring parts. The Mastra agent gathers the necessary context from `list_employees` and presents it to the reviewer for final sign-off.

Setup guide

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

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

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

Install the package using `npm install @mastra/mcp@latest`. Create a new `MCPClient` instance pointing to your server URL, then spread `mcpClient.listTools()` directly into your Mastra AI agent configuration.

Yes, you can configure `requireToolApproval` for sensitive endpoints like `list_timecards`. This pauses Mastra execution and prompts a manager to review the action before the agent accesses actual hours worked.

The Mastra workflow engine runs `list_locations` as an initial step to find the correct `location_uuid`. It then stores this ID in context, feeding it into subsequent tools like `list_departments` or `list_employees`.

Mastra automatically detects the transport type, supporting both Streamable HTTP and SSE. This means you can run your Homebase scheduling agents in serverless environments without worrying about connection pooling.

All operations run inside an ephemeral sandbox that isolates your Homebase credentials. The agent only accesses the specific fields returned by `get_employee_profile` during the execution lifecycle, and no data is persisted on the host.

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