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

Q: How do I initialize Daytona (Dev Workspaces) in Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your agent definition.

Q: Does Pydantic AI validate the Daytona (Dev Workspaces) API responses?

Yes. Every time the server returns data from getsandbox or listvolumes, Pydantic AI checks the response against the schema. Silent corruption is impossible.

Q: Can I limit API key creation in Pydantic AI?

You can. Exclude createapikey and deleteapikey from the exposed tools when configuring the MCP toolset.

Type-safe Daytona workspace management for Pydantic AI agents that demand strict runtime validation.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Sandbox Provisioning

Spinning up cloud environments requires exact parameters. When your agent calls `create_sandbox`, Pydantic AI validates the request payload against strict schemas before sending it over the wire. If the agent hallucinates a memory tier that doesn't exist, the framework throws a validation error immediately. The agent catches the error and retries with valid specs.

Manage State with Pydantic AI

Complex development workflows rely on exact environmental states. Agents use `list_sandboxes_paginated` to audit running workspaces, pulling back typed arrays of active instances. When a workspace is no longer needed, the agent triggers `stop_sandbox` or `delete_sandbox`. You never end up with orphaned instances because of a badly formatted API request.

Snapshot Control via MCP Server

Freezing an environment is critical for reproducible bugs. Your agent executes `create_snapshot` to capture the workspace exactly as it is. Later, another agent can call `activate_snapshot` to spin up that exact state. Because the tools run through Pydantic AI, you know the snapshot IDs match the expected UUID format.

Setup guide

Set up Daytona (Dev Workspaces) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "daytona-dev-workspaces-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Daytona (Dev Workspaces) tools.",
)

result = await agent.run("List recent Daytona (Dev Workspaces) transactions")
print(result.output)

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 Pydantic AI

Use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass this toolset directly to your agent definition.

Yes. Every time the server returns data from `get_sandbox` or `list_volumes`, Pydantic AI checks the response against the schema. Silent corruption is impossible.

You can. Exclude `create_api_key` and `delete_api_key` from the exposed tools when configuring the MCP toolset.

It gives you a standard interface. You swap between OpenAI and local models in Pydantic AI without rewriting any of the sandbox management logic.

The server processes active tokens and workspace URLs when running commands like `get_sandbox_preview_url`. Vinkius destroys the V8 isolate immediately after the request, leaving zero residual 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