How to Use the Holded MCP in Vercel AI SDK

Q: How do I connect the Holded MCP server to the Vercel AI SDK?

Install @ai-sdk/mcp. Instantiate createMCPClient with your transport URL, then pass mcpClient.tools() into your text generation function.

Q: Can the Vercel AI SDK create Holded invoices automatically?

Yes. When you expose createinvoice to your model, it maps user prompts to the required contact IDs and line items to generate the record.

Q: Does the Vercel AI SDK support OAuth for Holded users?

The client supports passing an authProvider in the configuration. You handle the user token exchange, and the integration manages the authenticated tool calls.

Q: How do I close the connection after fetching data?

Always call mcpClient.close() once your streaming function resolves. This prevents memory leaks in your Edge Functions.

Build Next.js dashboards that stream Holded financial data directly into your UI using 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

Connect your MCP Server to React

The `list_invoices` and `list_contacts` tools feed live Spanish and LATAM ERP data straight into your frontend components. Your AI client fetches the data via the MCP protocol and streams the JSON chunks to the browser before the database query even finishes. Users see customer records and sales histories populate in real-time. You skip the loading spinners entirely when pulling inventory counts with `list_products`.

Generate invoices from chat

The `create_invoice` tool requires a contact ID and an array of items to generate a formal tax document in Holded. You can wire this up to a standard text input where a user types a request to bill a client. The Vercel AI SDK parses the natural language, maps the entities to your CRM records, and executes the server-side action. That resulting PDF link or confirmation streams back to the chat window instantly.

Live financial dashboards

Pulling `list_expenses` and `list_payments` lets you build dynamic cash flow monitors. The LLM processes the raw expense arrays and formats them into structured props for your React charting libraries. You write zero custom API wrappers. This framework handles the tool execution loop, ensuring your finance team always looks at the exact same ledger numbers stored in the backend.

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

Install `@ai-sdk/mcp`. Instantiate `createMCPClient` with your transport URL, then pass `mcpClient.tools()` into your text generation function.

Yes. When you expose `create_invoice` to your model, it maps user prompts to the required contact IDs and line items to generate the record.

The client supports passing an `authProvider` in the configuration. You handle the user token exchange, and the integration manages the authenticated tool calls.

Always call `mcpClient.close()` once your streaming function resolves. This prevents memory leaks in your Edge Functions.

Vinkius runs the server in an ephemeral V8 isolate sandbox. Your `list_contacts` names and `list_invoices` totals pass directly to your endpoint token and disappear from our memory the millisecond the request completes.

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