How to Use the DVC MCP in Vercel AI SDK

Stream DVC experiment data directly into your Vercel AI SDK frontends for real-time model tracking.

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 Vercel AI SDK

Create your Vinkius account to connect DVC to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track experiments in your UI

Use `list_experiments` to pull your latest model runs into your application state. This lets your Vercel AI SDK components display live progress updates to users without blocking the main thread. Your app handles the stream directly, rendering experiment metadata as it arrives. You get immediate visibility into model performance without waiting for a full page refresh.

Manage projects with DVC

Call `list_projects` to populate dynamic dashboards within your interface. Your AI client can now switch between different ML workspaces instantly, keeping your development environment organized. Everything happens via the MCP server connection. You don't need to build custom wrappers to verify which project is active.

Audit user activity

Invoke `get_user` to verify session context and permissions for your DVC environment. This ensures your Vercel AI SDK logic only executes operations allowed by the current user profile. It provides a clear audit trail for every action. You keep the backend secure while your frontend remains responsive and fluid.

Setup guide

Set up DVC MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all DVC tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent DVC transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the required packages and initialize the client using your server endpoint. You pass the tools into your generation function to let the AI interact with your data.

Yes, the streaming architecture handles large payloads efficiently. You should implement pagination or filtering in your logic to keep the UI snappy.

No, the MCP server operates over an asynchronous connection. Your frontend remains fast because data fetches don't block your event loop.

Your data remains within your infrastructure. The server only processes the specific experiment metadata you request.

You manage security via standard environment variables or headers. The connection is encrypted, and you control access at the endpoint level.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.