How to Use the Daytona (Dev Workspaces) MCP in CrewAI

Q: Can CrewAI agents share Daytona (Dev Workspaces) sandboxes?

Yes. Because tools like getsandbox return standard JSON metadata, your developer agent can pass the sandbox ID to your tester agent through CrewAI's shared memory.

Q: How do I prevent a CrewAI agent from accidentally deleting a Daytona (Dev Workspaces) environment?

Use the toolfilter option in MCPServerHTTP to restrict access. You can hide destructive tools like deletesandbox while exposing safe tools like startsandbox and stopsandbox to your MCP agent.

Deploy specialized CrewAI agent teams to provision, test, and manage Daytona dev environments autonomously.

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 CrewAI

Create your Vinkius account to connect Daytona (Dev Workspaces) to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Environment Provisioning

Let a QA agent and a DevOps agent collaborate to prepare test environments. The DevOps agent calls `create_sandbox` to spin up the workspace, while the QA agent monitors the build status. Once the environment is ready, the QA agent uses `get_sandbox_preview_url` to run integration tests against the live port. If tests fail, the agents work together to diagnose the issue without human intervention.

Autonomous Sandbox Lifecycle Management via MCP Server

Deploy a moderator agent to keep your cloud spend down. This agent periodically calls `list_sandboxes` to check for inactive workspaces and automatically shuts them down using `stop_sandbox`. If a developer needs their workspace back, they ask the assistant, which triggers `start_sandbox` to wake it up. This MCP Server setup ensures you never leave expensive sandboxes running overnight.

Automated Snapshot and Archive Crews

Set up a dedicated backup crew that monitors your active development environments. The crew uses `create_snapshot` to capture daily progress and archives old work using `archive_sandbox`. If an environment gets corrupted, the recovery agent steps in, runs `recover_sandbox`, and restores the latest snapshot. It keeps your development team moving without manual infrastructure troubleshooting.

Setup guide

Set up Daytona (Dev Workspaces) MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Daytona (Dev Workspaces) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Daytona (Dev Workspaces) Analyst",
    goal="Access and analyze Daytona (Dev Workspaces) data via MCP.",
    backstory="Expert analyst with direct Daytona (Dev Workspaces) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Daytona (Dev Workspaces) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Daytona (Dev Workspaces) Analyst",
        goal="Access and analyze Daytona (Dev Workspaces) data via MCP.",
        backstory="Expert analyst with direct Daytona (Dev Workspaces) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Daytona (Dev Workspaces) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius Daytona endpoint URL directly into the agent's `mcps` list during initialization. CrewAI automatically discovers and configures all 28 tools for the agent over the MCP connection.

Yes. Because tools like `get_sandbox` return standard JSON metadata, your developer agent can pass the sandbox ID to your tester agent through CrewAI's shared memory.

Use the `tool_filter` option in `MCPServerHTTP` to restrict access. You can hide destructive tools like `delete_sandbox` while exposing safe tools like `start_sandbox` and `stop_sandbox` to your MCP agent.

Yes. You can define a sequential process where Agent A creates the workspace, Agent B configures the volume, and Agent C runs the test suite.

Vinkius executes all Daytona tool calls inside isolated, secure V8 sandboxes. Your raw source code and environment variables are never cached or stored on Vinkius servers, ensuring strict data privacy for your MCP integrations.

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