How to Use the Neptune.ai (ML Experiment Tracking) MCP in Claude

Q: Can Claude Desktop list all my registered models from Neptune.ai (ML Experiment Tracking)?

Yes, your agent uses the listmodels tool to pull the entire model registry for a project. It displays the model versions and their current states right inside your Claude Desktop interface.

Q: Can I manage multiple projects using Neptune.ai (ML Experiment Tracking) inside Claude Desktop?

Yes, the server uses listprojects to show your available workspaces. Your agent can then target a specific project with getproject to narrow down the scope of your run searches.

Q: Do I need to write custom Python scripts to compare my run parameters?

No, you just tell your agent what to compare. It uses getattributes to pull the exact parameters mapped within the experiment runtime bounds and displays them side-by-side.

Query Neptune.ai (ML Experiment Tracking) runs and pull metrics directly into your Claude Desktop chat via this MCP Server.

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 Claude Desktop

Create your Vinkius account to connect Neptune.ai (ML Experiment Tracking) to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find specific training runs inside Claude Desktop

The `search_runs` tool filters and extracts your historical ML runs based on exact parameters you define during chat. When you ask your agent to compare models, it queries your workspace to pull run details without forcing you to click around the web dashboard. This MCP tool lets you identify which learning rate produced the lowest loss directly in your conversation. Your agent formats the returned run data into clean markdown tables, letting you spot trends across dozens of experiments instantly.

Audit registered models using this MCP Server

The `list_models` tool queries your Neptune project to pull all registered model versions and their deployment states. Instead of leaving Claude Desktop to check which model is flagged for staging, you ask your agent to check the registry status directly. It retrieves the exact model metadata, helping you verify that your production candidates match the parameters logged during training. This keeps your deployment decisions grounded in actual logged run data.

Inspect workspace projects from your chat window

The `list_projects` tool fetches all active workspaces and projects associated with your credentials. Your agent uses this list to switch context or verify which project names are valid before starting deeper queries. It works alongside `get_project` to fetch specific project structures, ensuring your queries hit the right target. You don't have to memorize project IDs when starting a new analysis session.

Setup guide

Set up Neptune.ai (ML Experiment Tracking) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Neptune.ai (ML Experiment Tracking) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Neptune.ai (ML Experiment Tracking) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under neptuneai-ml-experiment-tracking-mcp.

json

{
  "mcpServers": {
    "neptuneai-ml-experiment-tracking-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 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 Claude Desktop

You ask your agent to find runs with specific parameters, and it calls the `search_runs` tool. It queries your Neptune workspace and displays the matching training runs directly in your chat.

Yes, your agent uses the `list_models` tool to pull the entire model registry for a project. It displays the model versions and their current states right inside your Claude Desktop interface.

Yes, the server uses `list_projects` to show your available workspaces. Your agent can then target a specific project with `get_project` to narrow down the scope of your run searches.

No, you just tell your agent what to compare. It uses `get_attributes` to pull the exact parameters mapped within the experiment runtime bounds and displays them side-by-side.

Your API tokens and experiment parameters never pass through external third-party servers. All requests to fetch run configurations and metrics run locally through the V8 sandbox, ensuring your proprietary model parameters remain private.

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