How to Use the E2B MCP in Vercel AI SDK

Q: How does E2B work with Vercel AI SDK?

You connect the E2B MCP server via the createMCPClient utility in your Vercel AI SDK project. This allows your agent to trigger code execution tools that run in secure, isolated VMs.

Q: How do I manage sandbox lifecycles?

Call createsandbox to start a session and killsandbox when finished. You should always ensure your cleanup logic runs to avoid keeping idle environments active.

Run code in isolated Firecracker microVMs directly from your Vercel AI SDK streams for real-time results.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect E2B MCP to Vercel AI SDK

Create your Vinkius account to connect E2B 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 E2B with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Instant isolated execution

Your Vercel AI SDK agent spawns a clean Linux environment in under 150ms. Using `create_sandbox`, you get a dedicated microVM every time your code needs to run. It keeps your production environment clean. Since the sandbox is ephemeral, you don't worry about state pollution or lingering background processes.

Real-time UI updates

Stream tool results from your MCP Server straight into your React or Next.js components. The AI client handles the output as it happens. Users stop staring at loading spinners while the backend computes. They see the data populate your UI components as the code finishes execution.

Precise resource management

Keep your infrastructure lean by tracking active sessions with `list_sandboxes`. You can query exactly what is running for any given user session. Once the work is done, use `kill_sandbox` to wipe the environment. This keeps your usage predictable and secures your application against resource hoarding.

Setup guide

Set up E2B 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 E2B 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 E2B 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 E2B. 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 E2B 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 E2B MCP in Vercel AI SDK

You connect the E2B MCP server via the `createMCPClient` utility in your Vercel AI SDK project. This allows your agent to trigger code execution tools that run in secure, isolated VMs.

Yes, E2B is designed for these environments. Because the sandboxes are ephemeral and start in 150ms, they integrate cleanly into your Vercel AI SDK workflow without adding significant latency.

Every sandbox runs in a Firecracker microVM, which isolates the process from your host. This ensures that even if your agent writes malicious code, it stays trapped within the sandbox.

Call `create_sandbox` to start a session and `kill_sandbox` when finished. You should always ensure your cleanup logic runs to avoid keeping idle environments active.

The server only touches the filesystem and memory within the specific microVM it creates. It never reads your Vercel AI SDK environment variables or local source code files.

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