Bring User Onboarding
to Vercel AI SDK
Learn how to connect Appcues to Vercel AI SDK and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Appcues MCP Server?
Connect your Appcues account to any AI agent and take full control of your in-app onboarding and automated user experience orchestration through natural conversation.
What you can do
- Experience Portfolio Orchestration — List and manage your entire portfolio of flows and checklists programmatically, retrieving detailed engagement metadata
- User & Event Intelligence — Programmatically monitor real-time user events and access behavioral metadata to coordinate your engagement strategy
- Segment & Targeting Architecture — Access your complete directory of user segments to coordinate your organizational resource allocation
- Performance Monitoring — Access real-time status updates for active flows and track individual completion metrics directly through your agent for instant reporting
- Operational Monitoring — Verify account-level API connectivity and monitor event ingestion volume directly through your agent for perfectly coordinated service scaling
How it works
1. Subscribe to this server
2. Retrieve your API Key and API Secret from your Appcues dashboard (Settings > API)
3. Start orchestrating your user growth from Claude, Cursor, or any MCP client
No more manual checking of individual flow completion rates or missing critical onboarding drop-offs. Your AI acts as your dedicated experience coordinator and user architect.
Who is this for?
- Product Managers — instantly retrieve experience performance recaps and monitor onboarding health using natural language commands
- Growth Leads — verify individual user metadata and track event history without leaving your creative workspace
- Developers — integrate high-speed Appcues engagement data into custom analytics and CRM tools through simple AI queries
Built-in capabilities (10)
Verify Appcues API connectivity
This action is irreversible. Delete a user from Appcues
Get flow details
Get segment details
Get user profile from Appcues
List all checklists
List all onboarding flows
List all user segments
The flow must be in draft or unpublished state. Publish a flow
Users will no longer see it until republished. Unpublish a flow
Why Vercel AI SDK?
The Vercel AI SDK gives every Appcues tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 10 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
- —
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
- —
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same Appcues integration everywhere
- —
Built-in streaming UI primitives let you display Appcues tool results progressively in React, Svelte, or Vue components
- —
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
Appcues in Vercel AI SDK
Appcues and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Appcues to Vercel AI SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Appcues in Vercel AI SDK
The Appcues MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Vercel AI SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Appcues for Vercel AI SDK
Every tool call from Vercel AI SDK to the Appcues MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find my Appcues API Key?
Log in to your account, navigate to Settings > API, and copy your unique API Key and Secret from the credentials section.
Can I check flow completion rates via AI?
Yes! The list_flows tool allows your agent to retrieve completion and interaction metadata for all your active experiences.
How do I list my user segments?
Use the list_segments tool to retrieve your complete directory along with the unique identifiers for all managed targeting groups.
How does the Vercel AI SDK connect to MCP servers?
Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
Can I use MCP tools in Edge Functions?
Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
Does it support streaming tool results?
Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.
createMCPClient is not a function
Install: npm install @ai-sdk/mcp