An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Neptuneai ML Experiment Tracking to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control your machine learning telemetry through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Neptune.ai.

  1. 01

    List projects

    This capability lists all the Neptune workspaces and projects you have access to.

  2. 02

    Get attributes

    Use this to pull specific parameters and metrics recorded during an experiment run.

  3. 03

    Get project

    This capability retrieves detailed information for a specific Neptune ML project.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Neptune.ai.

  1. 04

    Get user

    This capability fetches user credentials and availability details for your service account.

  2. 05

    List models

    This capability shows the trained models currently stored within a project.

  3. 06

    Search runs

    Use this to find specific ML experimentation runs inside a project.

Real work

What teams actually run

01

Real-time Progress Monitoring

Ask your agent for the latest accuracy metrics while a training job is running.

02

Model Version Auditing

Verify which specific model version is currently promoted to production.

03

Hyperparameter Analysis

Compare different experiment runs to see how parameter changes affected loss.

04

Workspace Management

Enumerate all accessible projects to get a clear view of your research footprint.

Automate a task

Put Neptune.ai to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Neptune.ai works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Neptune.ai to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

934ms average. Fast in production.

Neptune.ai is checked daily against the live service.

Daily averagePeak 1087ms
Oct 3Today
Fastest day
757ms
Slowest day
1087ms
14-day trend
Stable-2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Neptune.ai, so you can see the experience inside your AI.

It does not authenticate your account with Neptune.ai. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Neptune.ai Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_HI0D1zHVFTWAvCQH47Rd6lplgg0GBJXVQZ0fMTHm/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Neptune.ai capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "neptuneai-ml-experiment-tracking-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_HI0D1zHVFTWAvCQH47Rd6lplgg0GBJXVQZ0fMTHm/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Neptune.ai in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Neptune.ai owners hand off.

This MCP is built for technical teams managing complex machine learning lifecycles.

  • 01

    Data Scientists

    They ask the agent to monitor training progress and verify metrics without opening a browser.

  • 02

    ML Engineers

    They use the agent to audit the model registry and check attributes from their terminal.

  • 03

    AI Researchers

    They track production model versions and ensure metadata stays consistent across projects.

FAQ

Questions Neptune.ai owners ask.

  • 01

    How do I connect my Neptune.ai data to my AI client?

    You subscribe to the MCP on Vinkius and provide your Neptune.ai API Token. Once connected, you can use it immediately in Claude, Cursor, or Windsurf.

  • 02

    Can I see my training loss curves through the AI?

    Yes, the MCP allows your agent to extract telemetry like accuracy metrics and loss curves from specific execution checkpoints.

  • 03

    Does this work with my existing Neptune.ai projects?

    Yes, the MCP uses your API token to access the projects and workspaces already managed in your Neptune.ai account.

  • 04

    What kind of models can I manage?

    You can list and retrieve trained models that have been promoted or logged within your Neptune.ai project registry.

  • 05

    Is my API token secure?

    Vinkius manages your credentials and keeps them secure so you can connect your client once and stay connected.

  • 06

    Can I see the accuracy metrics for a specific ML run through my agent?

    Yes. Use the get_attributes capability with your Project ID and Run ID. Your agent will retrieve the detailed telemetry logged during that execution, including accuracy, loss, and any custom attributes defined in your code.

  • 07

    How do I check which model versions are currently stable in my registry?

    The list_models capability retrieves all packaged ML models within a project. Your agent will expose the promoted model versions, helping you distinguish between experimental runs and stable candidates ready for deployment.

  • 08

    Can my agent search through hundreds of past ML experimentation runs?

    Absolutely. Use the search_runs capability with your Project ID. Your agent will query Neptune's tracking server to identify historical experiment state checkpoints, making it easy to locate specific training results across your entire research timeline.

Explore

More in Developer Tools

Suggestions

Connect Neptune.ai to Claude, Cursor, ChatGPT & more