How to Use the Mailjet MCP in Vercel AI SDK

Q: How do I connect Mailjet to my Vercel AI SDK project?

Install @ai-sdk/mcp and initialize the MCP client using the Vinkius HTTP endpoint. Pass the tools generated by the client directly into your streamText or generateText functions. Make sure to close the client connection when the execution finishes.

Stream Mailjet operations directly to your frontend using the Vercel AI SDK for instant, real-time UI updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailjet MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send transactional emails directly from the edge

`send_transactional_email` sends transactional emails directly from your edge-rendered UI. Your users trigger verification messages or receipts, and the Vercel AI SDK streams the status updates straight to the screen. No more staring at a blank loading spinner while the backend works. Under the hood, this setup bypasses heavy server-side middleware. You configure the client to communicate with the Mailjet API, handling high-volume dispatches with minimal latency.

Synchronize Vercel AI SDK inputs with contact lists

`create_new_contact` registers new subscribers into your marketing database the millisecond they sign up. You can chain this with `add_contact_to_list` to place them into specific segments without writing custom sync cron jobs. The Vercel AI SDK handles the state transitions so the user gets immediate visual confirmation. This direct execution keeps your front-end state in lockstep with Mailjet. If a subscription fails, the UI renders the error message immediately, allowing the user to correct their input without page reloads.

Render live campaign metrics in your application

`get_campaign_performance` retrieves open rates, clicks, and bounce counts to populate your custom reporting views. By exposing this to the Vercel AI SDK, your internal tools can ask the agent to fetch and render performance charts on demand. The agent calls `list_marketing_campaigns` to find the target campaign ID, then pulls the raw metrics. Your React or Next.js components receive this data stream to paint tables and graphs without manual API integration. This MCP Server connection makes dashboard building an afternoon task instead of a sprint-long project.

Setup guide

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

Install `@ai-sdk/mcp` and initialize the MCP client using the Vinkius HTTP endpoint. Pass the tools generated by the client directly into your `streamText` or `generateText` functions. Make sure to close the client connection when the execution finishes.

Yes, the MCP client is fully compatible with Edge runtimes. Because Vinkius handles the underlying HTTP transport, your edge functions stay lightweight and execute within standard execution limits.

The SDK processes the tool output as it resolves, allowing your UI to show progress indicators for actions like `send_transactional_email`. This eliminates the need for polling endpoints to verify if an email went out.

The system returns the exact error payload from the Mailjet API back to your agent. Your application can catch this error in the SDK lifecycle and present a clean retry prompt to the user.

Vinkius runs the MCP Server in an isolated, zero-trust sandbox that never persists your contact data or campaign statistics. All payloads containing email addresses flow through encrypted transit and are immediately discarded from memory once the API call 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