How to Use the Mailchimp MCP in Vercel AI SDK

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

Use createMCPClient with your HTTP transport URL. Call mcpClient.tools() to expose the operations, then pass them to streamText. Always remember to call mcpClient.close() when the stream finishes.

Q: Can the Vercel AI SDK send Mailchimp campaigns?

Yes, it can. The sendcampaign tool triggers a live email send immediately. Since this action is irreversible, you should build a confirmation step into your frontend before executing the tool.

Q: Does the Mailchimp MCP Server support OAuth?

It does. You can pass an authProvider during your setup sequence. This allows end-users to authenticate their own accounts directly through your application interface.

Stream live Mailchimp metrics to your React frontend using this MCP Server and 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 Mailchimp MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Mailchimp stats via Vercel AI SDK

`list_audiences` and `get_audience` fetch subscriber counts and merge fields straight from the MCP Server. Your AI client streams this raw data right into your Next.js dashboard as it arrives. No loading spinners while waiting for API responses. The user sees their marketing metrics populate instantly. You just pass the tools to `streamText` and let the Vercel AI SDK handle the edge transport. It keeps your interface fast and reactive.

Render performance metrics in real-time

`get_report` pulls open and click rates for specific campaign IDs. Connect this MCP Server to your UI, and your users can ask for their latest email stats in plain English. The agent fetches the data and renders it as a chart widget instantly. Finding the right campaign is just as fast. `list_campaigns` grabs the IDs and send times. You get a fluid, conversational interface where marketers query their own data without logging into a separate platform.

Add contacts without form refreshes

`add_member` pushes new signups to your lists directly from a chat interface. If a user asks to subscribe, the agent handles the transaction silently in the background. It passes the exact status—subscribed, pending, or transactional—without breaking the conversation flow. You can also verify existing contacts using `search_members`. The AI checks if an email is already on the list before attempting an insert. This prevents duplicate errors and keeps your subscriber database clean.

Setup guide

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

Use `createMCPClient` with your HTTP transport URL. Call `mcpClient.tools()` to expose the operations, then pass them to `streamText`. Always remember to call `mcpClient.close()` when the stream finishes.

Yes, it can. The `send_campaign` tool triggers a live email send immediately. Since this action is irreversible, you should build a confirmation step into your frontend before executing the tool.

The SDK processes tool calls as fast as the LLM requests them. You will need to implement your own throttling or caching if you expect high traffic. Edge functions can quickly exhaust API quotas if left unchecked.

It does. You can pass an `authProvider` during your setup sequence. This allows end-users to authenticate their own accounts directly through your application interface.

Your agent handles raw email addresses, subscriber statuses, and tags. Vinkius runs these operations inside a zero-trust V8 Isolate Sandbox. Ephemeral execution means no contact records survive after the connection drops.

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