How to Use the Holded MCP in Vercel AI SDK

Q: How do I use the Holded MCP server with the Vercel AI SDK?

First, install the packages: npm install ai @ai-sdk/mcp. Then, use createMCPClient to connect to the server URL provided by Vinkius. You can then pass the tools from mcpClient.tools() into your generateText or streamText calls.

Q: Can my Vercel AI SDK app show a live list of Holded invoices?

Yes. You'll call streamText and prompt your agent to use the listinvoices tool. The Vercel AI SDK will stream the tool's output, allowing you to render each invoice in your UI as it's received from the Holded API.

Q: How can I update Holded product stock from my Vercel AI SDK frontend?

Your frontend code will trigger an AI call that uses the updateproductstock tool. You'll need to provide the product ID and the new stock quantity. The AI agent handles the API call through the MCP server.

Q: What's the best way to find a specific contact's ID in Holded?

Have your agent use the listcontacts tool first. This gives you a list of all contacts and their corresponding IDs. Once you have the ID, you can use getcontactdetails to pull the full profile for that specific person or company.

Stream Holded data directly into your UI. Build real-time business apps with the 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 Holded MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Business Dashboards

Stop forcing users to refresh the page. Use the Vercel AI SDK to stream data from `list_invoices` and `list_projects` directly into your React or Next.js components. The UI populates as the data arrives. This isn't just a static API call; it's a live data feed powered by the MCP server. You can build dashboards that show your clients an up-to-the-second view of their account activity, project status, or outstanding balances. It feels fast because it is.

Create Interactive Contact Forms

Let your users manage their Holded contacts without leaving your app. When a user asks your agent to "pull up John Doe's info," your app can use `get_contact_details` and stream the results right into the input fields of a form. This means no more copy-pasting for your users or context-switching between tabs. The AI does the fetching, and the Vercel AI SDK renders the data instantly. It’s a clean, direct way to interact with business data.

Real-Time Inventory Updates

Connect your UI directly to your inventory. A user can click a button in your app to trigger the `update_product_stock` tool, and the change happens immediately in Holded. Then, you can confirm the change by calling `get_product_details` and streaming the new stock count back to the UI. The whole process is visible to the user in real-time, confirming their action worked without a page load or waiting for a spinner.

Setup guide

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

First, install the packages: `npm install ai @ai-sdk/mcp`. Then, use `createMCPClient` to connect to the server URL provided by Vinkius. You can then pass the tools from `mcpClient.tools()` into your `generateText` or `streamText` calls.

Yes. You'll call `streamText` and prompt your agent to use the `list_invoices` tool. The Vercel AI SDK will stream the tool's output, allowing you to render each invoice in your UI as it's received from the Holded API.

Your frontend code will trigger an AI call that uses the `update_product_stock` tool. You'll need to provide the product ID and the new stock quantity. The AI agent handles the API call through the MCP server.

Have your agent use the `list_contacts` tool first. This gives you a list of all contacts and their corresponding IDs. Once you have the ID, you can use `get_contact_details` to pull the full profile for that specific person or company.

Your data, such as invoice details and contact profiles, is passed through a stateless, ephemeral sandbox on Vinkius. The server itself stores nothing; it's just a secure pipe from your Vercel AI SDK application to the Holded API. All connections are encrypted and your Vinkius token handles authentication.

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