How to Use the Appcues MCP in Mastra AI

Q: How do I configure the Appcues MCP Server in Mastra AI?

Install @mastra/mcp@latest and create a new MCPClient instance. Point the server URL to your Vinkius endpoint. Mastra automatically detects if the transport is Streamable HTTP or SSE.

Q: Can Mastra AI track custom Appcues events?

Your workflows can log anything. The trackuseractivity tool accepts JSON strings for profile updates and custom events. You just map your internal data to the required payload structure.

Q: Do I need to manually map the tools?

Not at all. You call mcpClient.listTools() and spread the results directly into your Agent's tool array. The framework handles the schema parsing natively.

Q: Is my Appcues segmentation data secure with this MCP Server in Mastra?

Audience rules pulled via getsegment stay within your execution environment. Vinkius routes the MCP traffic through an ephemeral V8 sandbox. We never store your targeting logic or customer identifiers.

Build resilient Mastra AI MCP workflows to automate flow publishing and user segmentation.

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 Mastra AI

Create your Vinkius account to connect Appcues to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Flow Publishing Workflows

Product teams frequently forget to turn off outdated announcements. Building a Mastra AI workflow solves this by checking `list_flows` every Friday. If a temporary banner is still active, the agent triggers `unpublish_flow` automatically. Network hiccups won't break your automation. Mastra's built-in exponential backoff means if the Appcues API drops a request, the workflow just tries again. You get reliable state management without writing custom retry logic.

Branching Logic for User Segments

Moving users between audiences requires precise timing. An agent can pull a specific audience using `get_segment`, analyze the criteria, and then decide what happens next. If the group is too small, it pauses; if it hits a threshold, it acts. Record updates happen right inside these branches. Your agent calls `track_user_activity` to log an event the moment a specific condition triggers. You build complex customer journeys entirely in code.

Safe Deployments with Mastra AI MCP Server

Releasing a new onboarding checklist to thousands of users carries risk. Mastra lets you require human approval before executing `publish_flow`. The agent prepares the release, stops, and waits for a manager to click okay. Payload reviews are straightforward. The reviewer checks the output from `list_checklists` and `get_account_details` to verify the target audience. Once approved, the workflow resumes and pushes the update live.

Setup guide

Set up Appcues MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Appcues tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "appcues-mcp-client",
  servers: {
    "appcues-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Appcues Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Appcues tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Appcues transactions"
);
console.log(result.text);

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 Mastra AI

Install `@mastra/mcp@latest` and create a new `MCPClient` instance. Point the server URL to your Vinkius endpoint. Mastra automatically detects if the transport is Streamable HTTP or SSE.

Your workflows can log anything. The `track_user_activity` tool accepts JSON strings for profile updates and custom events. You just map your internal data to the required payload structure.

The framework includes an automatic retry engine. If a call to `list_mobile_experiences` hits a rate limit, Mastra backs off and tries again later.

Not at all. You call `mcpClient.listTools()` and spread the results directly into your Agent's tool array. The framework handles the schema parsing natively.

Audience rules pulled via `get_segment` stay within your execution environment. Vinkius routes the MCP traffic through an ephemeral V8 sandbox. We never store your targeting logic or customer identifiers.

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