How to Use the Dubsado MCP in Vercel AI SDK

Q: How do I stream Dubsado invoice data using Vercel AI SDK?

Call getinvoice inside your streamText tool execution block to feed the billing JSON directly to your UI. The client receives the raw data chunk by chunk, rendering the invoice layout without blocking the main thread.

Q: Can Vercel AI SDK trigger a Dubsado workflow template?

Yes, you run applyworkflow by passing the template ID retrieved from listworkflowtemplates into your tool call. The SDK streams the execution steps so your user sees the onboarding phases activate one by one.

Q: What is the fastest way to list Dubsado projects in Vercel AI SDK?

Use the listprojects tool within a React Server Component to pull active files directly from the MCP Server. This setup bypasses custom backend routing, loading your client list on the edge.

Q: How does this MCP Server handle rate limits during peak client onboarding?

The server monitors headers on createproject and updateproject to prevent rate exhaustion. If you hit API limits, the connection passes the throttle status back to your frontend so you can gracefully pause the UI stream.

Q: Where does my Dubsado contract data go when using this MCP integration?

Your contract contents retrieved via getcontract remain inside the Vinkius sandboxed execution environment. No contract text or client signatures are stored on external servers, routing raw payload data straight to your Vercel AI SDK client.

Build live-streaming creative agency portals where Vercel AI SDK renders Dubsado project updates and invoices as they happen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dubsado MCP to Vercel AI SDK

Create your Vinkius account to connect Dubsado 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 Dubsado with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Dubsado setups in Vercel AI SDK

`create_project` initializes a new client workspace instantly, sending the raw payload straight to your React or Next.js frontend. Your user gets immediate visual feedback on their screen while the background execution handles the heavy lifting. From there, `apply_workflow` attaches your standard onboarding sequence without freezing the UI. Users watch their client dashboard populate with tasks in real-time, eliminating loading spinners.

Render dynamic invoices on the edge

`create_invoice` builds a billing record and streams the calculated line items directly into your edge-rendered application. This keeps the user session active and responsive, preventing timeout errors during high-traffic billing cycles. Next, `get_invoice` pulls the final payment status to update your frontend UI components instantly. Your clients see their payment link the millisecond Dubsado registers the record.

Track contract signatures with this MCP Server

`get_contract` fetches the current signature status and terms to display a live progress bar in your Next.js application. Your client sees exactly who needs to sign next without refreshing the page. By calling `list_contracts`, your Vercel AI SDK application builds a client-facing portal showing historical agreements. This direct data binding removes the need for slow, intermediate database synchronization.

Setup guide

Set up Dubsado 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 Dubsado 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 Dubsado 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 Dubsado. 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 Dubsado 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 Dubsado MCP in Vercel AI SDK

Call `get_invoice` inside your streamText tool execution block to feed the billing JSON directly to your UI. The client receives the raw data chunk by chunk, rendering the invoice layout without blocking the main thread.

Yes, you run `apply_workflow` by passing the template ID retrieved from `list_workflow_templates` into your tool call. The SDK streams the execution steps so your user sees the onboarding phases activate one by one.

Use the `list_projects` tool within a React Server Component to pull active files directly from the MCP Server. This setup bypasses custom backend routing, loading your client list on the edge.

The server monitors headers on `create_project` and `update_project` to prevent rate exhaustion. If you hit API limits, the connection passes the throttle status back to your frontend so you can gracefully pause the UI stream.

Your contract contents retrieved via `get_contract` remain inside the Vinkius sandboxed execution environment. No contract text or client signatures are stored on external servers, routing raw payload data straight to your Vercel AI SDK client.

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