How to Use the Homebase MCP in Vercel AI SDK

Q: How do I connect the Homebase MCP Server to my Vercel AI SDK project?

Install the core packages with npm install ai @ai-sdk/mcp. Initialize the client using createMCPClient with your HTTP endpoint, then pass mcpClient.tools() directly to streamText to start querying Homebase. Remember to call mcpClient.close() once the execution finishes to prevent memory leaks.

Q: How does Vercel AI SDK handle Homebase location IDs?

Your Vercel AI SDK agent will run listlocations first to map the human-readable branch name to its unique UUID. Once it has the UUID, it passes that identifier to downstream Homebase tools like listscheduledshifts automatically.

Q: Can I build Next.js schedule viewers with this?

Yes. You can pass user-specific tokens using the authProvider option when setting up your Vercel AI SDK client. This ensures that the agent only retrieves listtimecards or staff profiles for authorized Homebase locations.

Stream real-time shift data and timesheets directly into your Next.js application using the Homebase MCP Server and Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Homebase to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Active Clock-Ins to Vercel AI SDK

The `get_active_clock_ins` tool lets your Vercel AI SDK frontend display live Homebase labor data without lag. Your AI client fetches who is currently on the clock and streams that status directly to your Next.js user interface. This bypasses slow page reloads, letting Vercel AI SDK stream floor coverage to Homebase managers in real-time. By integrating `list_locations` first, your Next.js application resolves the correct branch ID before querying active staff. The Vercel AI SDK handles this handoff instantly, keeping your edge functions fast and your Homebase query UI responsive.

Verify Timesheets with Zero Loading Spinners

Your Vercel AI SDK client uses `list_timecards` to fetch actual hours worked and compare them to scheduled shifts. The model pulls Homebase timesheets and displays the raw hours to your admins mid-conversation. This lets Next.js users approve or flag entries dynamically. You don't need to build complex polling mechanisms. The Vercel AI SDK streams the output of `list_scheduled_shifts` alongside the actual Homebase timecards, showing discrepancies side-by-side as the model processes them.

Build Live Org Dashboards in Your Next.js Chat

Generate instant Homebase team charts and role lists in your Next.js app by calling `list_employees` and `list_defined_roles` via the MCP server. The Vercel AI SDK gathers your workforce structure and passes this data directly to your frontend components. This setup keeps your database clean and avoids heavy state management. Your Vercel AI SDK interface updates instantly as the model reads Homebase department structures via `list_departments` and profiles via `get_employee_profile`.

Setup guide

Set up Homebase MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Homebase tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Homebase transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the core packages with `npm install ai @ai-sdk/mcp`. Initialize the client using `createMCPClient` with your HTTP endpoint, then pass `mcpClient.tools()` directly to `streamText` to start querying Homebase. Remember to call `mcpClient.close()` once the execution finishes to prevent memory leaks.

Yes, this setup is fully compatible with Edge runtimes. Because the Vercel AI SDK client connects over standard HTTP transport, it avoids Node-specific APIs. You can fetch `list_labor_budgets` or employee profiles in lightweight, globally distributed functions.

Your Vercel AI SDK agent will run `list_locations` first to map the human-readable branch name to its unique UUID. Once it has the UUID, it passes that identifier to downstream Homebase tools like `list_scheduled_shifts` automatically.

Yes. You can pass user-specific tokens using the `authProvider` option when setting up your Vercel AI SDK client. This ensures that the agent only retrieves `list_timecards` or staff profiles for authorized Homebase locations.

The MCP server runs inside a zero-trust V8 Isolate sandbox, meaning your raw API keys never hit the browser. It only processes the specific data returned by `list_labor_budgets` or timesheet tools, keeping your core employee records hidden from public view.

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