How to Use the E2B MCP in Google ADK

Q: How do Google ADK agents manage the E2B microVM lifecycle?

Your agent calls createsandbox when it needs to execute code, and then triggers killsandbox when the task is done. The E2B platform enforces a 300-second maximum timeout if your agent fails to clean up.

Give your Google ADK enterprise agents secure, ephemeral sandboxes to run code and process BigQuery exports.

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 Google ADK

Create your Vinkius account to connect E2B to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Spin up microVMs for Google ADK agents

The `create_sandbox` tool builds an isolated Linux environment in 150 milliseconds for executing code. This tool lets your Google ADK agent run complex calculations on data pulled from Google Cloud services without host vulnerability. Your agent chooses from pre-configured templates like Python or Node. This keeps data processing fast, letting Gemini models analyze results immediately after code execution finishes.

Terminate active runtimes instantly

The `kill_sandbox` tool destroys a running microVM and wipes its filesystem to guarantee clean state. Your Google ADK agent calls this tool to free up resources immediately after finishing a data processing job. This active cleanup prevents lingering processes from running up your cloud bill. It ensures that every execution task starts from a blank slate with zero shared state.

Track E2B sandboxes within Google ADK

The `list_sandboxes` tool retrieves a list of all active microVMs currently running in your account. Your agent or orchestrator queries this MCP Server tool to audit active runtimes and manage concurrency limits. This tracking mechanism prevents resource starvation across large agent fleets. It gives you raw operational data to monitor how many parallel tasks your Gemini models are running.

Setup guide

Set up E2B MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with E2B tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="E2B_agent",
    model="gemini-2.0-flash",
    instruction="You have access to E2B tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate the McpToolset using the StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset directly into the tools list of your LlmAgent to expose the sandbox controls.

Yes, the MCP server supports both transport protocols. For production setups on Google Cloud, we recommend using the HTTP transport to keep your agent architecture clean and decoupled.

Your agent calls create_sandbox when it needs to execute code, and then triggers kill_sandbox when the task is done. The E2B platform enforces a 300-second maximum timeout if your agent fails to clean up.

Yes, you can use the optional tool name filter in the McpToolset configuration. This lets you expose only create_sandbox while keeping lifecycle management tools like kill_sandbox restricted to system orchestrators.

All files and code executed inside the sandbox are isolated within a single-use Firecracker microVM. Once your agent calls kill_sandbox or the timeout hits, the filesystem is destroyed, leaving no trace of your data on the host.

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