Bring Sandboxes
to OpenAI Agents SDK
Learn how to connect Daytona (Dev Workspaces) to OpenAI Agents SDK and start using 28 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Daytona (Dev Workspaces) MCP Server?
Connect your Daytona account to any AI agent to orchestrate cloud-based development environments through natural language. Daytona provides standardized, ephemeral sandboxes that can be provisioned and managed on demand.
What you can do
- Sandbox Orchestration — List, create, start, stop, and delete sandboxes with specific CPU, memory, and disk configurations.
- Snapshot Management — Create and manage snapshots to preserve environment states or activate them for new sandboxes using
create_snapshotandactivate_snapshot. - API Key Control — Manage your authentication keys directly, including listing and creating new access tokens via
list_api_keysandcreate_api_key. - Resource Scaling — Dynamically resize sandbox resources (vCPU, RAM, Disk) to match your workload requirements using
resize_sandbox. - Volume & Storage — Inspect and manage persistent volumes and snapshots for your dev environments.
How it works
- Subscribe to this server
- Enter your Daytona API Key
- Start managing your dev infrastructure from Claude, Cursor, or any MCP client
Who is this for?
- DevOps Engineers — Automate the lifecycle of test environments and sandboxes.
- Software Developers — Spin up fresh coding environments without leaving the chat or IDE.
- QA Teams — Quickly recover sandboxes from error states or fork existing environments for debugging.
Built-in capabilities (28)
Activate a snapshot
Archive a sandbox
Create a new Daytona API key
Create a new Daytona sandbox
Create a new snapshot
Create a new volume
Deactivate a snapshot
Delete an API key by name
Delete a sandbox
Delete a snapshot
Delete a volume
Fork an existing sandbox
Get details of a specific API key by name
Get details of the currently authenticated API key
Get details of a specific sandbox
Get a signed preview URL for a specific port on a sandbox
Get details of a specific snapshot
Get details of a specific volume by ID
Get details of a specific volume by name
List Daytona API keys
List all Daytona sandboxes
List all Daytona sandboxes (paginated)
List all Daytona snapshots
List all Daytona volumes
Recover a sandbox from an error state
Resize sandbox resources
Start a stopped sandbox
Stop a running sandbox
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 28 tools from Daytona (Dev Workspaces) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Daytona (Dev Workspaces), another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Daytona (Dev Workspaces) in OpenAI Agents SDK
Daytona (Dev Workspaces) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Daytona (Dev Workspaces) to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Daytona (Dev Workspaces) in OpenAI Agents SDK
The Daytona (Dev Workspaces) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 28 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Daytona (Dev Workspaces) for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Daytona (Dev Workspaces) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I change the resources of an existing sandbox?
Yes, you can use the resize_sandbox tool to update the CPU, memory, or disk size of a specific sandbox by providing its ID or name.
How do I create a new environment with a specific Docker image?
Use the create_sandbox tool and provide the image parameter with the desired Docker or OCI image name.
What should I do if a sandbox is in an error state?
You can use the recover_sandbox tool to attempt to restore a sandbox from an error state back to a functional one.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
CrossRef Alternative
13 toolsSearch 150M+ academic works — find journal articles, books, DOIs, citations and scholarly metadata.
Object Hash Engine
1 toolsGenerate deterministic SHA-256 fingerprints of any JSON object. Keys are automatically sorted so {b:2,a:1} and {a:1,b:2} always produce the exact same hash. Essential for deduplication.
GitScrum Knowledge
28 toolsBuild and query knowledge bases via GitScrum — manage notes as agent memory, maintain wiki pages, communicate through discussions, and search across all resources from any AI agent.
BlueSnap
10 toolsProcess and manage payments via BlueSnap — list transactions, subscriptions, and vaulted shoppers directly from any AI agent.