How to Use the Daytona (Dev Workspaces) MCP in Google ADK

Q: How do I configure Daytona (Dev Workspaces) with Google ADK?

Initialize McpToolset using the Vinkius endpoint URL. Pass it to your LlmAgent tools array. Gemini will automatically map the sandbox functions.

Q: Can Google ADK agents manage Daytona (Dev Workspaces) snapshots?

They can. Agents call createsnapshot to freeze a workspace state. This helps when building complex multi-step reasoning chains that might fail halfway through.

Q: What happens if a Daytona (Dev Workspaces) sandbox crashes during a Google ADK run?

The agent detects the failure and triggers recoversandbox. It can also pull the logs to diagnose why the crash happened in the first place.

Q: How does this setup handle my source code and API keys?

Tools like getcurrentapikey and listsandboxes expose your active environment states and credentials to the model. Vinkius sandboxes this execution so no persistent data leaks outside the immediate tool call.

Give your Google ADK agents isolated Daytona environments to execute code and test BigQuery pipelines.

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 Google ADK

Create your Vinkius account to connect Daytona (Dev Workspaces) 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 Daytona (Dev Workspaces) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scale Compute for Gemini Agents

Gemini's massive context window means agents write huge blocks of code. They need a place to run it. The `create_sandbox` tool spins up a Daytona environment perfectly sized for the task. If the agent hits a memory limit while processing Vertex AI datasets, it can call `resize_sandbox` to bump up the specs. The agent controls its own compute resources dynamically.

Fork Environments via MCP Server

Testing destructive database migrations requires isolation. An agent can read a production schema, then execute `fork_sandbox` to build a safe replica environment. The agent tests the migration in the fork. Once verified, it grabs a signed link via `get_sandbox_preview_url` and sends it to your Slack for approval.

Volume Management for Data Tasks

Analyzing large datasets requires persistent storage. Your agent uses `create_volume` to attach a dedicated drive before pulling records from BigQuery. When the analysis finishes, the agent runs `archive_sandbox` to save money. The volume remains intact for the next agent run. You clean up later with `delete_volume`.

Setup guide

Set up Daytona (Dev Workspaces) 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 Daytona (Dev Workspaces) 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="Daytona (Dev Workspaces)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Daytona (Dev Workspaces) 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 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 Google ADK

Initialize `McpToolset` using the Vinkius endpoint URL. Pass it to your `LlmAgent` tools array. Gemini will automatically map the sandbox functions.

They can. Agents call `create_snapshot` to freeze a workspace state. This helps when building complex multi-step reasoning chains that might fail halfway through.

Vinkius uses a zero-trust architecture. You only need a single endpoint token, and the execution environment is completely isolated from your core GCP infrastructure.

The agent detects the failure and triggers `recover_sandbox`. It can also pull the logs to diagnose why the crash happened in the first place.

Tools like `get_current_api_key` and `list_sandboxes` expose your active environment states and credentials to the model. Vinkius sandboxes this execution so no persistent data leaks outside the immediate tool call.

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