How to Use the Appcues MCP in Vercel AI SDK

Q: How do I stream Appcues flow details using the Vercel AI SDK?

Call getflow inside your streamText tool call. The SDK pipes the raw JSON properties straight to your React UI components without blocking the main thread.

Q: Can the Vercel AI SDK trigger an Appcues unpublish action?

Yes, by passing unpublishflow to your tool definitions. The SDK lets your custom admin dashboard send the unpublish command with a single text prompt.

Q: How does Vercel AI SDK handle Appcues segment evaluation?

It uses listsegments to retrieve your target groups. The SDK then evaluates these rules at the edge to decide which components to render for the active user session.

Q: Do I need a separate backend to check Appcues status?

No, you do not. This MCP Server exposes checkappcuesstatus which your edge functions can execute directly through the SDK's transport layer.

Stream Appcues onboarding flows and segment data directly to your 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 Appcues MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Appcues flow states live with the Vercel AI SDK

This MCP Server uses `list_flows` to pull your active onboarding patterns and pipe them straight to your React or Next.js components. Your AI client grabs the list and renders the interactive steps on the screen before the user has time to look for a refresh button. You do not need to wait for heavy backend payloads. The Vercel AI SDK handles the stream, rendering live UI components as `get_flow` extracts the exact steps your users need to see.

Live user segment lookups during AI chat

This MCP Server runs `get_user` to fetch real-time profile data and adjust the user's interface on the fly. Your frontend reads the user's current status and changes what they see based on their actual Appcues history. Combining this with `get_segment` lets you toggle UI features dynamically. The Vercel AI SDK feeds these segment details directly into your edge functions to personalize the layout instantly.

Instant checklist rendering in your web app

This MCP Server targets onboarding bottlenecks by calling `list_checklists` to show users exactly what they need to finish. It skips the traditional API polling lag by feeding the data straight into your streaming UI. If a user gets stuck, your Vercel AI SDK setup can trigger `check_appcues_status` to confirm the connection is active before drawing the next step. You keep the interface snappy without writing custom polling code.

Setup guide

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

Call `get_flow` inside your streamText tool call. The SDK pipes the raw JSON properties straight to your React UI components without blocking the main thread.

Yes, by passing `unpublish_flow` to your tool definitions. The SDK lets your custom admin dashboard send the unpublish command with a single text prompt.

It uses `list_segments` to retrieve your target groups. The SDK then evaluates these rules at the edge to decide which components to render for the active user session.

No, you do not. This MCP Server exposes `check_appcues_status` which your edge functions can execute directly through the SDK's transport layer.

The server processes Appcues user profiles and segment details inside an isolated V8 sandbox. Your API keys never touch the browser, and the connection closes immediately after the tool execution finishes.

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