How to Use the Evoliz MCP in Vercel AI SDK

Q: How do I install the Evoliz MCP server for Vercel AI SDK?

Run npm install ai @ai-sdk/mcp in your project. Then initialize the MCP server connection using createMCPClient with your Evoliz endpoint URL.

Q: Can Vercel AI SDK stream the results of Evoliz invoice queries?

Yes. When your agent calls listinvoices, the Vercel AI SDK streams the raw data back to your React or Svelte frontend in real time.

Q: Do I need to close the connection in my edge functions?

You must call mcpClient.close() after your agent finishes executing its tools. This prevents memory leaks and hanging connections in serverless environments.

Connect the Evoliz MCP server to your Vercel AI SDK apps and stream French accounting data directly into your React or Next.js frontends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evoliz MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream French Tax Compliance Live

When your agent calls `list_invoices` or `list_quotes`, the Vercel AI SDK streams the resulting JSON directly into your Next.js frontend. You don't have to wait for the entire request to finish. The data pipes straight to the browser. This means your users watch their accounting dashboard populate in real time. You get instant UI updates for French business compliance data instead of staring at a loading spinner while the API fetches records.

Build Interactive Client Portals

Your agent can fetch specific records using `get_client` and `get_invoice` to render dynamic billing pages. Since Vercel AI SDK routes requests through edge functions, these lookups happen close to your users to cut round-trip latency. You can also let users update their own details. The `create_client` tool handles new customer onboarding right from your chat interface, automatically enforcing required fields like name and business type.

Render Product Catalogs Instantly

Pull pricing and service details on demand with `list_articles` and `get_article`. Your AI client reads the catalog and instantly generates tailored quotes for your leads. When the user approves the pricing, the agent calls `get_quote` to check the details before finalizing the transaction. The entire flow happens inside your UI, wired into the Vercel AI SDK streaming architecture and the MCP standard.

Setup guide

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

Run `npm install ai @ai-sdk/mcp` in your project. Then initialize the MCP server connection using `createMCPClient` with your Evoliz endpoint URL.

Yes. When your agent calls `list_invoices`, the Vercel AI SDK streams the raw data back to your React or Svelte frontend in real time.

You must call `mcpClient.close()` after your agent finishes executing its tools. This prevents memory leaks and hanging connections in serverless environments.

The server interacts directly with the Evoliz API, which enforces strict French anti-fraud regulations. Your agent creates records using `create_client` that inherently follow these mandatory formats.

Your invoice and quote data stays protected. The Vinkius V8 Isolate Sandbox ensures that when your agent reads a specific invoice, that memory space is destroyed immediately after execution.

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