How to Use the Daytona (Dev Workspaces) MCP in OpenAI Agents SDK

Q: How do I connect Daytona (Dev Workspaces) to OpenAI Agents SDK?

Pass the Vinkius endpoint via MCPServerStreamableHttp into your agent constructor. Set cacheToolsList=True so it discovers the sandbox tools instantly.

Q: Does Daytona (Dev Workspaces) work with OpenAI Agents SDK handoffs?

Yes. One agent can run forksandbox to isolate a bug, then hand the new environment ID to a specialized debugging agent.

Manage ephemeral Daytona workspaces safely using OpenAI Agents SDK handoffs and tracing.

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 OpenAI Agents SDK

Create your Vinkius account to connect Daytona (Dev Workspaces) to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision Workspaces from OpenAI Agents SDK

Your agent needs an isolated environment to execute code. Using `create_sandbox`, the agent spins up a fully configured Daytona workspace on demand. You define the guardrails. Before the agent calls `start_sandbox` or `stop_sandbox`, OpenAI's safety constraints validate the action. This keeps rogue agents from burning through cloud compute budgets.

Manage Stateful Snapshots

Long-running agents often need to pause and resume work. They can trigger `create_snapshot` to save the exact state of a workspace before handing off tasks to a specialized agent. When the next agent takes over, it calls `activate_snapshot`. The environment restores instantly. You track the entire sequence through the dashboard tracing built into the OpenAI Agents SDK.

Persistent Volumes for CI/CD

Sometimes an agent needs to share data across multiple ephemeral runs. It runs `create_volume` to mount persistent storage independent of the sandbox lifecycle. Agents can attach these volumes to new environments later. If an error occurs, the agent executes `recover_sandbox` while keeping the volume data intact.

Setup guide

Set up Daytona (Dev Workspaces) MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Daytona (Dev Workspaces) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Daytona (Dev Workspaces) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Daytona (Dev Workspaces) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Daytona (Dev Workspaces) Agent",
            instructions="You have access to Daytona (Dev Workspaces) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Pass the Vinkius endpoint via `MCPServerStreamableHttp` into your agent constructor. Set `cacheToolsList=True` so it discovers the sandbox tools instantly.

Yes. You handle this within the agent's tool configuration. Block destructive actions like `delete_sandbox` while allowing `get_sandbox_preview_url` for human review.

The server handles the authentication and tool schema formatting automatically. Your agent immediately understands how to format a `resize_sandbox` request without custom prompt engineering.

Yes. One agent can run `fork_sandbox` to isolate a bug, then hand the new environment ID to a specialized debugging agent.

The server reads your environment variables, sandbox configurations, and API keys via `list_api_keys`. Vinkius runs this in an ephemeral V8 isolate, meaning token access dies the second your session ends.

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