How to Use the DVC MCP in AutoGen

Q: How do AutoGen agents collaborate to review a DVC project?

One agent calls getproject to inspect the workspace, while another runs listexperiments to check recent runs. They discuss the results in a shared chat to decide the next step.

Q: Can an AutoGen agent assign tasks based on DVC user profiles?

Yes. The agent calls getuser to identify the project owner. It can then direct questions or alerts to that specific user during the conversation.

Q: How do AutoGen agents handle conflicting DVC views?

The auditing agent calls listviews to compare configurations. It debates the differences with the developer agent to determine which view is correct for the current run.

Let multiple AutoGen agents debate and select the best DVC models.

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 AutoGen

Create your Vinkius account to connect DVC to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent model selection via this MCP Server

Build a collaborative pipeline where agents analyze your training runs. One agent calls `list_experiments` to pull the latest metrics, while another agent evaluates the training cost. They debate the tradeoffs directly in your conversation loop. This setup prevents bad deployments. The agents must reach a consensus on whether the latest run meets your performance and budget thresholds before promoting it.

Collaborative project state verification

Ensure your workspace is clean before running new training jobs. An agent uses the MCP Server to run `list_projects` and `get_project` to inspect the workspace state. If it detects uncommitted changes, it alerts the developer agent. The agents work together to resolve the conflict. They check the active user profile via `get_user` to assign ownership of the uncommitted work, keeping your pipelines organized.

Automated dataset view auditing

Stop training on bad data splits. A data auditor agent calls `list_views` and `get_view` to inspect the data distribution. It then reports its findings to the training agent. If the data split is skewed, the auditor agent flags the issue. The training agent then pauses the run, saving you valuable GPU hours.

Setup guide

Set up DVC MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes DVC tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="DVC_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent DVC data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="DVC_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent DVC data")
    print(result.messages[-1].content)

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 AutoGen

One agent calls `get_project` to inspect the workspace, while another runs `list_experiments` to check recent runs. They discuss the results in a shared chat to decide the next step.

Yes. The agent calls `get_user` to identify the project owner. It can then direct questions or alerts to that specific user during the conversation.

The auditing agent calls `list_views` to compare configurations. It debates the differences with the developer agent to determine which view is correct for the current run.

Yes. You can connect the server using either stdio or Streamable HTTP transports. AutoGen's McpToolAdapter handles the schema conversion automatically.

The server uses token-based authentication handled directly by Vinkius. Your experiment parameters, project views, and user profiles are transmitted over encrypted channels and never logged.

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