How to Use the Daytona (Dev Workspaces) MCP in Claude Code

Q: How do I get preview links from the terminal?

Tell your agent to expose the port. It will execute getsandboxpreviewurl and print the signed HTTP link straight to standard output, allowing you to open it in a local browser.

Manage ephemeral infrastructure from your terminal by giving Claude Code direct access to your Daytona environments.

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 Claude Code

Create your Vinkius account to connect Daytona (Dev Workspaces) to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Operations via MCP Server

SREs don't want to click through web interfaces to manage dev environments. You pipe a command to Claude Code, and it runs `list_sandboxes` to audit running instances. It finds the stale workspaces and terminates them via `archive_sandbox` directly from your shell. This integration brings full infrastructure control to the command line. If a developer complains about a broken environment, your terminal agent executes `recover_sandbox` to fix the state, completely bypassing the GUI.

Automated CI/CD Workspace Provisioning

Pipeline automation gets much easier when your AI client can spin up environments on demand. Claude Code runs inside your GitHub Action, triggering `create_sandbox` to build an isolated container for end-to-end testing. State management is built right in. The agent creates a baseline using `create_snapshot` before running destructive database tests. If a test fails, it calls `activate_snapshot` to reset the environment for the next run, keeping your pipeline fast and reliable.

Storage and Key Administration

Provisioning persistent storage usually requires manual Terraform runs. Now your terminal agent calls `create_volume` to allocate space, verifies the allocation with `get_volume`, and mounts it to the active sandbox automatically. Security credentials get the same treatment. Claude Code audits your active tokens using `list_api_keys` and prunes compromised or expired credentials by invoking `delete_api_key`. Everything happens via headless execution in your terminal window.

Setup guide

Set up Daytona (Dev Workspaces) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see daytona-dev-workspaces-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Daytona (Dev Workspaces) transactions." It will automatically discover and invoke the available Daytona (Dev Workspaces) tools.

Terminal

claude mcp add --transport http daytona-dev-workspaces-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Daytona (Dev Workspaces) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "daytona-dev-workspaces-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

Run claude mcp add --transport http daytona -- in your terminal. Make sure all flags come before the server name. Use claude mcp list to verify the connection.

Yes, it runs perfectly in headless environments. You can trigger Claude Code inside a Docker container or SSH session to provision sandboxes, run tests, and clean up resources automatically.

Your terminal agent gets full access to the snapshot API. It can list, create, activate, and delete snapshots to maintain clean states across your ephemeral dev environments.

Tell your agent to expose the port. It will execute `get_sandbox_preview_url` and print the signed HTTP link straight to standard output, allowing you to open it in a local browser.

Vinkius isolates the execution environment completely. The integration only processes operational data like volume names, snapshot IDs, and sandbox configurations. The connection drops immediately after the command executes, leaving no persistent access.

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