How to Use the Alegra MCP in Vercel AI SDK

Q: How do I connect the Alegra MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and initialize the client using your Vinkius endpoint. Pass the server tools directly into the tools parameter of streamText to let your LLM call Alegra operations.

Q: What happens if an Alegra tool call fails during a stream?

The SDK catches the error from tools like createinvoice and transmits the error state in the stream. Your UI catches this signal to show an inline error message rather than crashing the chat session.

Stream real-time Alegra invoice and inventory updates directly into your Next.js frontend using 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 Alegra MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Alegra UI rendering with Vercel AI SDK

The `list_invoices` tool fetches sales records from Alegra and streams them directly to your React components without loading spinners. Your users watch their invoice lists populate row by row as the Vercel AI SDK handles the active HTTP stream. Behind the scenes, the `get_invoice_details` tool feeds metadata straight into your Edge Functions using the MCP protocol. You get instant UI rendering because the data flows through a single, open connection instead of waiting for a full API payload to resolve.

Direct contact setup via streaming text inputs

The `create_contact` tool registers new client profiles in Alegra the moment your user finishes typing their details. Your Vercel AI SDK application binds this tool to a chat input, turning casual conversations into structured customer records. By calling `get_contact_details` immediately after, your frontend confirms the saved profile layout on the fly. No manual page refreshes are required since the client UI updates the local state using the raw tool output.

Interactive stock checking in your React frontend

The `list_inventory_items` tool pulls current stock levels from Alegra to answer inventory queries inside your chat interface using this MCP Server. Your Vercel AI SDK setup processes this data on the edge, routing stock numbers straight to custom UI widgets. When stock runs low, the frontend triggers `get_item_details` to show alternative products instantly. This keeps your inventory display accurate up to the second, preventing out-of-stock orders before they happen.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the client using your Vinkius endpoint. Pass the server tools directly into the `tools` parameter of `streamText` to let your LLM call Alegra operations.

Yes, this MCP Server runs in a lightweight sandbox compatible with Edge runtimes. You can call tools like `list_payments` without hitting cold starts or execution limits.

The SDK streams tool calls as they happen, meaning the UI renders the estimate list layout while the data is still arriving. This eliminates the blank screens usually associated with heavy ERP queries.

The SDK catches the error from tools like `create_invoice` and transmits the error state in the stream. Your UI catches this signal to show an inline error message rather than crashing the chat session.

Vinkius runs this MCP Server in an isolated V8 sandbox, meaning your raw invoice and payment payloads never persist on external disks. The Vercel AI SDK receives data over an encrypted TLS connection, keeping your financial records strictly between your app and Alegra.

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