How to Use the Neptune.ai (ML Experiment Tracking) MCP in Vercel AI SDK

Q: What tools are available for model auditing?

The server provides listmodels and getattributes. Your agent uses these to look up specific model versions in your registry and verify their training parameters.

Q: How is my ML experiment metadata secured during transit?

All training parameters and run metrics fetched by getattributes are processed in ephemeral V8 sandboxes. No experiment metadata is stored on disk, and connections are encrypted end-to-end.

Feed live Neptune.ai (ML Experiment Tracking) metrics directly into your Vercel AI SDK frontend with zero UI lag.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neptune.ai (ML Experiment Tracking) MCP to Vercel AI SDK

Create your Vinkius account to connect Neptune.ai (ML Experiment Tracking) 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 Neptune.ai (ML Experiment Tracking) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream run searches to Vercel AI SDK frontends

Stop making your users wait for heavy ML dashboards to load. This MCP Server lets your Vercel AI SDK application fetch active run parameters directly from your workspace. By calling `search_runs`, the AI retrieves exact experiment details and streams the raw JSON straight to your UI components as it arrives. You do not need to build complex polling APIs or state management systems. The SDK handles the streaming connection while `get_attributes` pulls specific metrics, letting developers display live loss curves and hyperparameter sets in custom React or Next.js views instantly.

Audit models on the edge

Edge functions require lightweight, fast execution. This server uses the V8 sandbox to connect your edge-rendered Vercel AI SDK app to your Neptune workspaces. The AI agent calls `list_models` to check registry states without cold-start penalties or heavy dependency bundles. When a developer asks about a specific model version, your agent invokes `get_project` to fetch the metadata. The response streams back immediately, keeping your serverless functions fast and your API bills low.

Interactive project discovery

Users can browse their entire machine learning workspace via chat. By exposing `list_projects` to your Vercel AI SDK setup, you let users query their run history using plain English instead of clicking through a heavy web interface. Your conversational UI calls `get_user` to verify who is asking before showing sensitive workspace data. This keeps the discovery phase fast, secure, and entirely conversational.

Setup guide

Set up Neptune.ai (ML Experiment Tracking) 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 Neptune.ai (ML Experiment Tracking) 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 Neptune.ai (ML Experiment Tracking) 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 Neptune.ai. 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 Neptune.ai (ML Experiment Tracking) 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 Neptune.ai (ML Experiment Tracking) MCP in Vercel AI SDK

You configure the MCP Server client in your route handler and pass the tools to the streaming engine. When a user asks for run metrics, the agent calls `search_runs` and streams the JSON chunks directly to the frontend.

Yes, the integration runs on edge-compatible endpoints. The MCP Server uses lightweight HTTP transport to execute `get_attributes` or `list_models` without heavy Node.js dependencies.

You pass your API token via the Vinkius single endpoint configuration. Your Vercel AI SDK code only needs one MCP token to access `list_projects` securely, keeping credentials hidden from the client side.

The server provides `list_models` and `get_attributes`. Your agent uses these to look up specific model versions in your registry and verify their training parameters.

All training parameters and run metrics fetched by `get_attributes` are processed in ephemeral V8 sandboxes. No experiment metadata is stored on disk, and connections are encrypted end-to-end.

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