How to Use the DVC MCP in CrewAI

Deploy specialized agents in CrewAI to manage DVC experiments and model lifecycle operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DVC MCP to CrewAI

Create your Vinkius account to connect DVC 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 DVC with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate ML model crews

Use `list_experiments` to give your research agents visibility into the current training state. A dedicated monitor agent tracks these results and alerts your human team if accuracy drops. This specialization keeps your agents focused. While one handles data, the other performs the audit.

Access DVC project state

Call `get_project` to provide your CrewAI agents with the necessary context for their specific roles. Each agent knows exactly which project to query, preventing cross-contamination. It makes collaboration between agents predictable. They share the same source of truth for all ML operations.

Streamline view management

Use `list_views` to help your agents navigate complex dataset structures. A moderator agent can verify view availability before the rest of the crew starts their work. It adds an extra layer of validation to your operations. You avoid wasting resources on invalid runs.

Setup guide

Set up DVC 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 DVC tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent DVC 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="DVC Analyst",
        goal="Access and analyze DVC data via MCP.",
        backstory="Expert analyst with direct DVC access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent DVC 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 DVC. 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 DVC 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 DVC MCP in CrewAI

Yes, you assign the tools to specific agents. They will use their own logic to decide when to query your experiment history.

You use tool filters to restrict which agents can call which functions. This ensures only authorized agents handle your project data.

Absolutely, the agents can switch projects as needed. You just define the agent scope in your crew setup.

Your experiment data is accessed over a secure, isolated connection. The agents only see what you allow them to see.

They only read project configurations and experiment logs. No sensitive raw data leaves your environment without your explicit control.

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

Mastra AI sdk-typescript

Start using the DVC MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started