How to Use the Cloudify MCP in Vercel AI SDK

Q: How do I hook up Cloudify to the Vercel AI SDK?

Install @ai-sdk/mcp and ai in your project. Create an HTTP transport pointing to your Vinkius MCP endpoint, then pass the tools from mcpClient.tools() directly into your streamText function.

Q: How does the Vercel AI SDK handle long-running Cloudify executions?

Your agent uses listexecutions to check active workflows. Since the SDK streams responses, the agent writes status updates to the UI chunk-by-chunk while the deployment runs.

Q: Do I need to manually map Cloudify schemas for my frontend?

No, because getblueprint returns structured JSON schemas that your agent parses automatically. The SDK then pipes these typed blocks straight into your React components.

Stream live Cloudify deployment states directly into your Next.js frontend using 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 Cloudify MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect live blueprints in your AI SDK UI

The `list_blueprints` tool lets your TypeScript AI agent pull active deployment schemas directly into your application's edge runtime. You get raw JSON structures immediately, allowing your frontend to render visual architecture maps without waiting for a backend API middleman. By feeding `get_blueprint` results into your streaming text components, your users watch the AI dissect complex node configurations in real-time. This cuts out loading spinners entirely because the JSON chunks stream into the UI as soon as the Cloudify MCP Server returns them.

Track active deployments live on the edge

The `list_deployments` tool queries your active runtime topologies to show exactly what resources are currently running in your cloud. Your Vercel AI SDK client grabs these structural states on the fly using the MCP, feeding the raw topology data straight into your React components. When a deployment gets stuck, the agent uses `get_deployment` to inspect the failing nodes. It renders the exact structural issue on screen, giving your users immediate feedback instead of a generic timeout error.

Monitor execution workflows in real-time

The `list_executions` tool exposes active workflow boundaries and cluster limits to your streaming client. This means your agent can track a running deployment step-by-step and feed those status updates directly to your user's browser. If you need to check which plugins are driving the current setup, the agent calls `list_plugins` to check native deployment limits. It pipes these capabilities straight to your edge function, keeping your frontend updated without extra database queries.

Setup guide

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

Install `@ai-sdk/mcp` and `ai` in your project. Create an HTTP transport pointing to your Vinkius MCP endpoint, then pass the tools from `mcpClient.tools()` directly into your `streamText` function.

Yes, because the server runs on Vinkius and connects over standard HTTP SSE. Your Vercel AI SDK client calls it from any edge route without hitting cold start delays or bundle size limits.

Your agent uses `list_executions` to check active workflows. Since the SDK streams responses, the agent writes status updates to the UI chunk-by-chunk while the deployment runs.

No, because `get_blueprint` returns structured JSON schemas that your agent parses automatically. The SDK then pipes these typed blocks straight into your React components.

Your blueprint schemas and deployment topologies never touch external LLM training loops. Vinkius runs the MCP Server in an isolated sandbox, keeping your cloud configuration data locked down.

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