How to Use the DVC MCP in Mastra AI

Build reliable ML workflows in Mastra AI with DVC experiment tracking and project management.

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 Mastra AI

Create your Vinkius account to connect DVC to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate experiment audits

Use `list_experiments` within your Mastra AI workflow to monitor model training status. The agent detects if a run fails and triggers your recovery logic automatically. It removes manual oversight from your pipeline. You define the logic, and the agent executes the audit steps based on real-time data.

Control DVC project views

Call `get_view` to extract specific dataset slices for your agent to analyze. This ensures your Mastra AI workflows always process the correct data version before starting a task. It prevents errors caused by stale inputs. You can branch your workflow if the view metadata indicates a mismatch.

Execute project operations

Use `list_projects` and `get_project` to manage multiple workspaces from a single agent. Your Mastra AI agent can switch contexts based on the specific job requirements. It simplifies complex operations. You just define the project scope, and the agent handles the rest.

Setup guide

Set up DVC MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All DVC tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "dvc-mcp-client",
  servers: {
    "dvc-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "DVC Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to DVC tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent DVC transactions"
);
console.log(result.text);

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 Mastra AI

You register the MCP server as a tool provider within your agent configuration. The agent then gains the ability to query your experiment history.

Yes, you can define workflows that trigger these tools at intervals. The agent handles the execution and any necessary retries.

The server connection is lightweight and designed for high-frequency use. Your agents will execute tasks with minimal latency.

Use the built-in tool approval features to gate sensitive operations. You can require human confirmation before the agent executes any destructive command.

The agent only accesses experiment logs and project configurations. It does not touch your raw model weights or training files unless you explicitly authorize it.

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