How to Use the DVC MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK handle multiple DVC projects?

Yes. The agent uses listprojects to find all active workspaces and getproject to inspect a specific one. You can use specialized agents to manage different projects and hand off tasks between them.

Run production-ready DVC experiment audits with built-in safety guardrails using the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect DVC to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit runs safely with the OpenAI Agents SDK

The `list_experiments` tool exposes your DVC model run history directly to your OpenAI agent. You get the exact parameters, metrics, and commit hashes without leaving your agent runtime loop. It's easy for the agent to parse this history and compare performance across your DVC training runs. Because you're running this DVC MCP server in a production OpenAI Agents SDK, you can set strict guardrails around how the agent reads training data. The OpenAI agent pulls the DVC experiment list, checks the metrics, and passes the clean data to your downstream evaluation steps.

Track dataset states across agent handoffs

Use `get_view` and `list_views` to let specialized OpenAI agents hand off specific DVC dataset slices to each other. Your data prep agent isolates a DVC view, and your training agent pulls that exact slice to start a run. This keeps your pipeline modular. We run this DVC MCP server in a secure Vinkius sandbox to handle the underlying state during OpenAI agent transitions. The OpenAI dashboard traces every single DVC view request, so you'll know exactly which agent accessed what data split.

Manage project structures via MCP Server tools

The `list_projects` and `get_project` tools give your OpenAI agent a clear map of your active DVC ML repositories. The agent checks the DVC project state before triggering any new training jobs to ensure everything is aligned. No more running training scripts on dirty git trees. Your OpenAI agent uses `get_user` to verify who ran a specific DVC experiment before saving it. This builds a clear audit trail in the OpenAI dashboard that links every model version to a specific team member.

Setup guide

Set up DVC MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all DVC tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives DVC tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate DVC tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="DVC Agent",
            instructions="You have access to DVC tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and use the HTTP streamable server class. You point it to your Vinkius endpoint, pass it to your Agent constructor, and the tools register automatically. Your agent can immediately call `list_experiments`.

Yes. The agent uses `list_projects` to find all active workspaces and `get_project` to inspect a specific one. You can use specialized agents to manage different projects and hand off tasks between them.

You can set the cache flag to true when setting up your connection parameters. This prevents the agent from making redundant network calls to `list_views` or `list_experiments` during complex reasoning loops.

You define guardrails in your agent configuration. By wrapping tools like `get_view` in validation functions, you ensure the agent only reads approved data slices.

We run the connection inside an isolated Vinkius container. Your ML experiment metadata, git hashes, and project configurations are encrypted in transit and never stored on our host system.

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