How to Use the Daytona (Dev Workspaces) MCP in Mastra AI

Q: How do I register Daytona (Dev Workspaces) tools within a Mastra AI agent?

Install @mastra/mcp and instantiate the client with your Vinkius URL. Fetch the tools using listTools() and spread them directly into your agent's MCP tool configuration array.

Q: Can Mastra AI handle human approval before modifying Daytona (Dev Workspaces) resources?

Yes. You can configure Mastra's requireToolApproval setting on critical tools like deletesandbox or resizesandbox so an admin must approve the action over the MCP connection before it runs.

Build resilient, self-healing developer workflows that spin up and configure Daytona workspaces using Mastra AI.

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 Mastra AI

Create your Vinkius account to connect Daytona (Dev Workspaces) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Self-Healing Sandboxes in Mastra AI Workflows

When a workspace build fails during an automated run, Mastra AI uses its conditional branching to catch the error. Your workflow automatically triggers `recover_sandbox` to restore the environment without manual developer intervention. If the recovery fails, the workflow uses Mastra's built-in exponential backoff to retry, eventually calling `delete_sandbox` if it cannot be saved. This keeps your active workspace list clean and prevents orphan processes from burning your budget.

Automated Volume Management via MCP Server

Use Mastra's workflow engine to manage persistent storage across your test runs. The agent can invoke `create_volume` to set up persistent disks before running a test suite, ensuring your data survives sandbox restarts. Once the tests finish, this MCP Server lets your Mastra agent call `delete_volume` to clean up. This ensures you only pay for storage when your automated pipelines are actively running.

Branching Snapshot Pipelines

Build complex testing pipelines that branch based on sandbox state. Your Mastra agent can call `create_snapshot` to save a baseline configuration, then run parallel test suites on different forks. If a specific test branch fails, Mastra's workflow engine can call `deactivate_snapshot` and roll back to a known good state. This makes regression testing entirely automated and reliable.

Setup guide

Set up Daytona (Dev Workspaces) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Daytona (Dev Workspaces) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "daytona-dev-workspaces-mcp-client",
  servers: {
    "daytona-dev-workspaces-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Daytona (Dev Workspaces) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Daytona (Dev Workspaces) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Daytona (Dev Workspaces) transactions"
);
console.log(result.text);

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 Mastra AI

Install `@mastra/mcp` and instantiate the client with your Vinkius URL. Fetch the tools using `listTools()` and spread them directly into your agent's MCP tool configuration array.

Yes. You can configure Mastra's `requireToolApproval` setting on critical tools like `delete_sandbox` or `resize_sandbox` so an admin must approve the action over the MCP connection before it runs.

Mastra has built-in retry logic with exponential backoff. If `create_sandbox` hits a rate limit or a temporary network hiccup, Mastra automatically pauses and retries the call safely.

Yes. Mastra can execute multiple steps in parallel, calling `create_sandbox` for each concurrent test run and tracking their progress independently via the MCP protocol.

Vinkius manages the authentication layer, meaning your Mastra workflows only need a single endpoint token. Your actual Daytona API keys are encrypted at rest and never exposed to the agent executing the workflow.

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