How to Use the DVC MCP in Claude

Q: How does Claude Desktop handle large DVC project histories?

The listprojects tool fetches a lightweight index of your workspaces to prevent performance lag. Claude Desktop only requests deep details when you ask about a specific run.

Audit ML experiments and track DVC project states directly inside Claude Desktop.

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 Claude Desktop

Create your Vinkius account to connect DVC to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit ML experiments inside Claude Desktop

The `list_experiments` tool pulls your entire ML training history directly into your Claude Desktop chat window. Your agent reads the parameters, metrics, and git commits to compare runs without you switching to a terminal. When Claude Desktop runs as a local subprocess, it uses this tool to parse local metadata. You get instant summaries of which model configuration performed best during your last training run.

Track project environments with this DVC MCP Server

The `list_projects` and `get_project` tools let Claude Desktop verify the state of your active machine learning workspaces. Your agent queries these tools to inspect directory layouts and data registries. This setup avoids manual context switching when configuring new training pipelines. Claude Desktop maps out the project structure and flags missing data dependencies before you start.

Query custom dataset views on demand

The `list_views` and `get_view` tools expose specific slices of your data registry directly to Claude Desktop. Your agent uses them to confirm which data subsets are assigned to which training splits. By feeding these views directly into the chat, this MCP integration helps you spot data leakage issues. You see exactly what your model sees during training.

Setup guide

Set up DVC MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The DVC MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the DVC MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under dvc-mcp.

json

{
  "mcpServers": {
    "dvc-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Open your Claude Desktop configuration file and add the server definition to your local configuration. Restart the app, and the DVC tools will appear immediately in your chat input.

No, Claude Desktop does not execute raw terminal commands. It uses structured tools like `list_experiments` to query your metadata safely.

The `list_projects` tool fetches a lightweight index of your workspaces to prevent performance lag. Claude Desktop only requests deep details when you ask about a specific run.

Yes, your local machine needs access to the repository. The MCP connection uses the local transport layer to query the files.

All your training metrics and dataset paths remain local to your machine. The Vinkius sandbox ensures that Claude Desktop only accesses this data during your active chat session, never storing it externally.

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