How to Use the Instantly MCP in Vercel AI SDK

Q: How do I stream Instantly campaign metrics using Vercel AI SDK?

You pass the tools from this MCP Server directly into streamText or generateText. When the agent calls getcampaignanalytics, the JSON payload streams straight to your Next.js or React frontend, updating the UI instantly without waiting for the complete execution to finish.

Q: How does the Instantly MCP Server handle lead uploads in Vercel AI SDK?

The agent uses addleads to inject raw JSON lead lists directly into your specified campaigns. You can stream the confirmation of each added lead back to the client UI, giving users instant visual feedback of the upload progress.

Q: Can I list active Instantly sender accounts with Vercel AI SDK?

Absolutely. Your agent calls listaccounts to fetch the status of all connected inboxes and streams the list straight to your frontend. This lets users monitor domain health and warm-up statuses without manual dashboard checks.

Build live cold outreach dashboards that stream real-time campaign stats using the Vercel AI SDK and this Instantly MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Instantly MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live sender stats to your React interface

Stop making users wait for cold email data to load behind a spinner. When your Vercel AI SDK app calls `get_account_stats`, the raw sender health metrics stream directly into your UI components as they arrive. This lets you build live-updating dashboards where sales teams watch their sending domain health tick up or down in real-time. Your interface stays responsive because the MCP Server handles the heavy lifting of talking to the API. If a domain shows warning signs, your users can instantly trigger a pause without page refreshes, keeping their sender reputation safe.

Watch leads populate in campaigns as they stream

Feeding new prospects into your outbound sequences shouldn't feel like a black box. By pairing the SDK with `add_leads`, your Next.js frontend displays each successfully imported contact the millisecond the server confirms it. You get a live, scrolling feed of lead injection instead of a static success message. This direct streaming connection means your users can verify exactly which subsequences are receiving contacts via `list_subsequences` while the import runs. If the import hits a snag, the error streams straight to the UI so they can fix formatting issues on the fly.

Direct Instantly campaign control with Vercel AI SDK

Build interactive control panels where users pause or resume sequences with a single click. When your agent invokes `pause_campaign` or `resume_campaign`, the status change streams instantly to the DOM, updating the button states immediately. The UI reflects the true state of your outbound operations by pulling fresh data through `get_campaign` right after the action completes. It keeps your sales reps in perfect sync with what is actually running in their outbound queues.

Setup guide

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

You pass the tools from this MCP Server directly into `streamText` or `generateText`. When the agent calls `get_campaign_analytics`, the JSON payload streams straight to your Next.js or React frontend, updating the UI instantly without waiting for the complete execution to finish.

Yes. Your agent can evaluate incoming deliverability metrics and instantly trigger `pause_campaign` if bounce rates spike. Because the Vercel AI SDK supports edge functions, this call executes with minimal latency to protect your domains.

The agent uses `add_leads` to inject raw JSON lead lists directly into your specified campaigns. You can stream the confirmation of each added lead back to the client UI, giving users instant visual feedback of the upload progress.

Absolutely. Your agent calls `list_accounts` to fetch the status of all connected inboxes and streams the list straight to your frontend. This lets users monitor domain health and warm-up statuses without manual dashboard checks.

Completely. Your API keys, cold email lead lists, and sender credentials never pass through any third-party intermediate servers. Vinkius runs this MCP Server in an isolated, ephemeral V8 sandbox, ensuring your private campaign data goes directly from your edge function to the target API endpoint.

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