How to Use the Mailshake MCP in Vercel AI SDK

Q: How do I integrate Mailshake with Vercel AI SDK?

Install @ai-sdk/mcp and set up the MCP HTTP transport pointing to your Vinkius endpoint. Pass the tools from mcpClient.tools() directly into generateText or streamText to let your model run campaigns.

Q: Can I stream Mailshake campaign metrics to my React UI using the Vercel AI SDK?

Yes. By calling listengagementactivity through the SDK's streaming functions, you can display open and click events on your frontend as they stream from the server, eliminating loading lags.

Q: How does the Vercel AI SDK handle pausing Mailshake campaigns?

The model invokes pausecampaign or resumecampaign as standard tools. The SDK handles the execution, updates the UI state, and then you call mcpClient.close() to clean up the connection.

Build live-updating sales dashboards and interactive outreach tools that stream Mailshake campaign data directly into your Vercel AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailshake MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live campaign lists into React with Vercel AI SDK

Stop making users wait for cold outreach metrics to load behind a spinner. This MCP Server lets your Vercel AI SDK frontend fetch campaign lists using `list_campaigns` and immediately render them as the data streams in. Your users see active campaigns populate their dashboards in real time, making cold email management feel instantaneous. By feeding `get_campaign_details` directly into `streamText`, you can build interfaces where users ask about active sequences and watch the performance numbers render segment by segment. No complex state management is needed, as the MCP Server returns the campaign metadata directly to your rendering components.

Turn chat prompts into live prospects in your Next.js UI

When an agent decides to add a new contact, it triggers `add_prospects` and displays the newly added leads on the screen instantly. Your Next.js interface updates the prospect list without requiring a manual page refresh, keeping your sales reps focused on hot targets. You can combine this with `list_campaign_recipients` to show real-time enrollment status directly in your custom sales app. The streaming responses allow your users to see exactly which prospects are being injected into their outbound sequences as it happens.

Interactive lead status updates with zero lag

Let your AI client update prospect stages on the fly by binding `update_lead_status` to your Vercel AI SDK tool calling setup. When a sales rep marks a lead as won or ignored in the chat UI, the server executes the update instantly, changing the prospect's status in Mailshake. You can also use `pause_prospect` to stop outreach immediately when a lead replies negatively. Because the SDK handles the MCP transport lifecycle, these commands execute with low latency, keeping your campaign lists clean and your deliverability rates safe.

Setup guide

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

Install `@ai-sdk/mcp` and set up the MCP HTTP transport pointing to your Vinkius endpoint. Pass the tools from `mcpClient.tools()` directly into `generateText` or `streamText` to let your model run campaigns.

Yes. By calling `list_engagement_activity` through the SDK's streaming functions, you can display open and click events on your frontend as they stream from the server, eliminating loading lags.

The model invokes `pause_campaign` or `resume_campaign` as standard tools. The SDK handles the execution, updates the UI state, and then you call `mcpClient.close()` to clean up the connection.

Yes. This MCP Server is compatible with Edge environments, meaning you can run tool calls like `get_user_profile` inside lightweight, global functions without cold-start delays.

Your prospect email addresses and campaign data are isolated within Vinkius's secure sandboxed MCP environment. The API keys never touch the client-side code, keeping your database safe from public exposure.

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