How to Use the Daytona (Dev Workspaces) MCP in Vercel AI SDK

Q: How do I connect Daytona (Dev Workspaces) to my Vercel AI SDK project?

Install @ai-sdk/mcp and set up the HTTP transport for your MCP Server pointing to your Vinkius endpoint. Register the Daytona tools using createMCPClient and pass them directly into your streamText function call.

Q: How does Vercel AI SDK handle long-running Daytona (Dev Workspaces) tasks?

It streams the intermediate states. When calling createsandbox, your UI receives the immediate sandbox metadata and can poll getsandbox to update the loading bar on your React page.

Q: Is it possible to fork an environment with this setup?

Yes. You can call forksandbox through the client, which spins up an identical copy of the workspace, and then you can stream the new preview URL to the user.

Spin up and manage ephemeral Daytona dev environments in real-time directly inside your Vercel AI SDK React or Next.js frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daytona (Dev Workspaces) MCP to Vercel AI SDK

Create your Vinkius account to connect Daytona (Dev Workspaces) 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 Daytona (Dev Workspaces) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

On-Demand Sandbox UI in Vercel AI SDK

When your user asks for a fresh workspace, Vercel AI SDK feeds that request straight to Daytona. Your app triggers `create_sandbox` and streams the build status directly to the screen, so users see their environment spinning up in real-time without stared-at loading spinners. After the build, you can grab a signed URL with `get_sandbox_preview_url` to embed a live preview of their running web server directly inside your React component. It runs on Edge Functions, keeping the connection fast and keeping your main server load at zero.

Live Workspace Scaling via Daytona MCP Server

Don't let your frontend hang when a workspace runs out of memory. If your customer is compiling a massive project, this MCP Server lets your application call `resize_sandbox` on the fly to bump up CPU and RAM allocations. The Vercel AI SDK handles the stream, letting the user watch their workspace limits expand. When they finish, you can shut down resources with `stop_sandbox` to keep your infrastructure costs under control.

Snapshot Previews Directly in Your Stream

Let users branch their work instantly. The user requests a backup, and your UI calls `create_snapshot` behind the scenes, capturing the exact state of their workspace without halting their current MCP workflow. You can then use `activate_snapshot` to let them load older versions of their environment. Vercel AI SDK outputs these transitions instantly, making state management feel like a local git branch.

Setup guide

Set up Daytona (Dev Workspaces) 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 Daytona (Dev Workspaces) 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 Daytona (Dev Workspaces) 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 Daytona. 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 Daytona (Dev Workspaces) 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 Daytona (Dev Workspaces) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and set up the HTTP transport for your MCP Server pointing to your Vinkius endpoint. Register the Daytona tools using `createMCPClient` and pass them directly into your `streamText` function call.

Yes. The Vinkius endpoint handles the heavy lifting, meaning your Edge Functions only need to make lightweight HTTP calls to trigger actions like `create_sandbox`.

It streams the intermediate states. When calling `create_sandbox`, your UI receives the immediate sandbox metadata and can poll `get_sandbox` to update the loading bar on your React page.

Yes. You can call `fork_sandbox` through the client, which spins up an identical copy of the workspace, and then you can stream the new preview URL to the user.

Your Daytona API keys and sandbox code never touch persistent storage on Vinkius, and everything runs under a zero-trust model where session tokens expire automatically.

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