How to Use the Daftra MCP in Vercel AI SDK

Q: How do I list invoices from Daftra using the Vercel AI SDK and this MCP server?

You pass the listinvoices tool to the streamText function. The Vercel AI SDK handles invoking the tool via the MCP server, and you can process the streaming results to display the invoice list in your UI as it's being fetched.

Q: Can I create new Daftra clients with the Vercel AI SDK?

Yes. The createclient tool is included. Your agent can call it to add a new client to your Daftra account, and it will return the new client's ID upon success.

Q: What's the best way to search for clients in Daftra through my Vercel AI SDK app?

Use the searchclientsbyname tool. It's designed for exactly this. Your agent can take a partial name from the user, call the tool, and stream the matching client profiles back to your application.

Build React UIs that stream Daftra data right into your components. With the Vercel AI SDK, your users see results live, not a loading spinner.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daftra MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Client Dashboards

Give your agent the `get_client_details` and `list_invoices` tools. Your user can ask for a client's status, and the Vercel AI SDK will stream the contact info, balance, and invoice history directly into your UI components as the data arrives. Instead of waiting for a full API response, your frontend populates in real-time. The user watches the information appear on screen, field by field. It's a much better experience than staring at a loading animation.

Create Interactive Inventory Search

Build an inventory search that feels instant. Your agent gets access to `list_inventory_products`, letting it find items in your Daftra catalog based on a user's conversational query. Because the AI SDK streams the tool output, your app can display products as they are found. This turns a simple search into an interactive experience where the user sees the AI working for them, right in the browser.

Real-time Reporting with this MCP Server

This Daftra MCP Server lets you build real-time financial dashboards for internal use. Hook up the `list_expenses` and `list_invoices` tools to an agent in your admin panel. You just ask your agent to 'show me this month's expenses,' and you can watch the list build itself on your screen. It’s a fast way to get a pulse on your business without having to log into another system and run a report.

Setup guide

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

You pass the `list_invoices` tool to the `streamText` function. The Vercel AI SDK handles invoking the tool via the MCP server, and you can process the streaming results to display the invoice list in your UI as it's being fetched.

Yes. The `create_client` tool is included. Your agent can call it to add a new client to your Daftra account, and it will return the new client's ID upon success.

Use the `search_clients_by_name` tool. It's designed for exactly this. Your agent can take a partial name from the user, call the tool, and stream the matching client profiles back to your application.

It's handled for you. You get a single Vinkius endpoint token that you plug into your `createMCPClient` configuration. You don't need to manage Daftra's specific OAuth or API keys in your frontend code.

Your Daftra data is only ever in transit. We're talking client names, contact info, and invoice line items. Vinkius processes it inside an ephemeral sandbox that's destroyed the moment the request is done. Nothing is logged or stored.

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