How to Use the DVC MCP in VS Code Copilot

Q: Can VS Code Copilot modify our DVC project configurations?

No, the tools are read-only. VS Code Copilot uses getproject to inspect your workspace but cannot alter your pipeline files.

Q: How does VS Code Copilot retrieve user profiles for DVC projects?

The getuser tool fetches the profile of the developer associated with a run. Copilot uses this to show who ran which experiment during your team reviews.

Share DVC experiment tracking and project views across your team inside VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect DVC to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Share workspace tracking via VS Code Copilot MCP Server

The `list_projects` tool allows VS Code Copilot to index your team's active training workspaces. By checking this index, the agent understands the exact structure of your shared ML repository. Committing this configuration to your repository means every developer gets the same context. Copilot answers questions about data directories without anyone needing to search the docs.

Audit team experiment history in the editor

The `list_experiments` tool retrieves your team's complete training log directly inside the VS Code Copilot chat. Your agent reads the metrics and loss curves to explain why a specific model run failed. This makes peer reviews faster. Instead of opening a separate dashboard, your team reviews code changes alongside the actual experiment results retrieved by the MCP Server.

Verify data views before deployment

The `get_view` tool pulls the precise configuration of your dataset splits directly into VS Code Copilot. Your agent uses this data to confirm that your validation and test sets are correctly isolated. This prevents training bias before you deploy. Copilot checks the view parameters and flags any overlapping data paths in your evaluation scripts.

Setup guide

Set up DVC MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the DVC MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the DVC tools listed. Try asking: "List my recent DVC transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a config file in your repository root. When your team pulls the repo, VS Code Copilot loads the MCP tools automatically.

No, the tools are read-only. VS Code Copilot uses `get_project` to inspect your workspace but cannot alter your pipeline files.

The `get_user` tool fetches the profile of the developer associated with a run. Copilot uses this to show who ran which experiment during your team reviews.

No, VS Code Copilot requires an active connection to process agent requests. The tools query your project metadata locally but need the Copilot network to run.

Your pipeline structures and metrics are processed within Vinkius's zero-trust sandbox. No experiment metadata is cached or used for training external models.

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