How to Use the Mailingwork MCP in Vercel AI SDK

Q: How do I connect Mailingwork to the Vercel AI SDK?

Install @ai-sdk/mcp and define a client using createMCPClient. Pass the HTTP transport URL for your Vinkius instance. Call mcpClient.tools() and feed that array into your streamText function.

Q: Can the Vercel AI SDK read Mailingwork subscriber tags?

Yes. The agent calls listtags to pull the available segmentation labels. It then applies those exact tags when updating a profile.

Q: Does this MCP setup support OAuth for user-specific data?

You pass an authProvider during the MCP client initialization. This ensures the agent only accesses lists and campaigns the current logged-in user has permission to view.

Build real-time marketing dashboards by streaming Mailingwork data directly into your React frontend 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 Mailingwork MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Mailingwork MCP Server Data Live

The `list_mailings` and `get_mailing` tools pipe campaign performance metrics straight into your Vercel AI SDK application. When an end user asks for an update on their latest newsletter, the agent fetches the data and streams it into your Next.js frontend instantly. You skip the loading spinners. The AI generates the text summary while simultaneously rendering the open rates and click data on the screen.

Manage Subscribers from the UI

Give your users direct control over their lists using `create_subscriber` and `update_subscriber`. An agent intercepts a natural language request like "add john@example.com to the VIP list" and executes the exact API call required. It grabs the correct list ID via `list_lists` first. This ensures the contact lands in the right segment. The frontend updates immediately as the tool returns a success confirmation.

Trigger Automations and Transactional Mail

Fire off immediate responses using `send_transactional_email` right from your application logic. If a user completes a specific action in your Svelte app, the agent handles the confirmation message delivery. You can also kick off complex drip campaigns by calling `trigger_automation`. The Vercel AI SDK manages the tool execution while keeping the user informed of the workflow status in real-time.

Setup guide

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

Install `@ai-sdk/mcp` and define a client using `createMCPClient`. Pass the HTTP transport URL for your Vinkius instance. Call `mcpClient.tools()` and feed that array into your `streamText` function.

Yes. The agent calls `list_tags` to pull the available segmentation labels. It then applies those exact tags when updating a profile.

The SDK catches the MCP tool execution error and passes it back to the language model. The agent can then retry the request or generate a fallback response for the user interface.

You pass an `authProvider` during the MCP client initialization. This ensures the agent only accesses lists and campaigns the current logged-in user has permission to view.

Vinkius runs the integration inside an ephemeral V8 Isolate Sandbox. When your agent processes subscriber email addresses and consent flags, the memory wipes completely after the session closes. Zero data persists on the middleware layer.

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