How to Use the cloudlayer.io MCP in Vercel AI SDK

Q: How do I connect the cloudlayer.io MCP Server to a Vercel AI SDK project?

Install @ai-sdk/mcp and create an MCP client pointing to your Vinkius endpoint. Pass the tools from mcpClient.tools() directly to streamText to let your agent call the document generation tools.

Q: How does the Vercel AI SDK handle cloudlayer.io rate limits?

Your agent can run getcloudlayerusagestats to check your current quota before triggering a heavy export. This prevents your Edge runtime from throwing errors when limits are reached.

Q: Can I receive async generation updates via webhooks?

Yes, use listcloudlayerwebhooks to see where your generation events are going. Your SDK application can listen to these endpoints to update the UI when long-running PDFs are ready.

Render PDFs and screenshots live in your Next.js app with the Vercel AI SDK and the cloudlayer.io 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 cloudlayer.io MCP to Vercel AI SDK

Create your Vinkius account to connect cloudlayer.io 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 cloudlayer.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream raw HTML to PDF with Vercel AI SDK

Your users hate loading spinners. When they click export, this MCP Server lets your agent trigger `convert_html_to_pdf` and stream the document generation state straight to your React UI. The Vercel AI SDK manages the connection so the page doesn't freeze while the engine builds the document. By avoiding heavy backend queues, you render the final file on the fly. Your agent feeds the raw HTML into the tool, catches the PDF stream, and presents it to the client without making them wait for a page refresh.

Capture live site screenshots in the UI

Use `capture_url_screenshot` to grab pixel-perfect images of any public address. The Vercel AI SDK streams the resulting image URL directly into your active chat component, letting users see the webpage render in real time. Your agent handles the layout adjustments based on the viewport. Because the SDK handles the data transfer at the edge, the image loads instantly in the browser without blocking the main thread.

Manage Nunjucks templates from your agent

Stop hardcoding invoice layouts. Your agent can use this MCP setup to call `list_pdf_templates` and `get_template_configuration` to inspect your active Nunjucks setups directly inside your app workspace. The Vercel AI SDK lets you display these template configurations to your users instantly. They can tweak fields in the UI and watch the agent regenerate the layout using the live credentials.

Setup guide

Set up cloudlayer.io 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 cloudlayer.io 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 cloudlayer.io 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 cloudlayer.io. 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 cloudlayer.io 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 cloudlayer.io MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and create an MCP client pointing to your Vinkius endpoint. Pass the tools from `mcpClient.tools()` directly to `streamText` to let your agent call the document generation tools.

Yes, the MCP Server runs in a V8 sandbox on Vinkius, which makes it compatible with Vercel's Edge runtime. Your agent calls `convert_url_to_pdf` without hitting cold starts or execution limits.

Your agent can run `get_cloudlayer_usage_stats` to check your current quota before triggering a heavy export. This prevents your Edge runtime from throwing errors when limits are reached.

Yes, use `list_cloudlayer_webhooks` to see where your generation events are going. Your SDK application can listen to these endpoints to update the UI when long-running PDFs are ready.

The server processes your raw HTML strings and target URLs inside an ephemeral V8 sandbox. Generated PDFs are written directly to secure storage, and your source code never exposes API keys to the client browser.

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