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

Q: Can Cascade use this MCP toolset to automate checks?

Yes. Cascade can run listmodels and compare different iterations in the background while you write code, alerting you if parameters mismatch.

Let Cascade chain multi-step queries across your Neptune.ai (ML Experiment Tracking) workspaces without leaving your Windsurf editor.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit training runs using the Windsurf MCP Server

The Neptune.ai (ML Experiment Tracking) MCP Server lets you audit and compare your training runs directly within your editor. This integration lets Cascade automatically scan your workspaces using `list_projects` to locate the exact project, then run queries over your training history. Cascade chains these steps in one shot. It calls `search_runs` to pull the top twenty runs, filters them by loss metric, and presents the exact parameters that caused the spike. You get answers in seconds without manual clicking.

Inspect model parameters instantly

Querying parameters with `get_attributes` lets you inspect hyperparameter changes across different training iterations instantly. Your agent uses this tool to pull specific logged parameters directly into your workspace. Cascade reads your active file, notices the model version you are editing, and automatically queries `list_models` to check if that run matches your local configuration. It stops you from deploying the wrong weights.

Verify workspace access and user configurations

Verifying your environment with `get_project` ensures you are always pointing to the correct workspace and team setup. This integration uses the tool to fetch metadata and verify your destination. If a query fails, Cascade uses `get_user` to check your active credentials and permissions. You get a clear diagnostic report right in your editor sidebar instead of a cryptic connection error.

Setup guide

Set up Neptune.ai (ML Experiment Tracking) MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Neptune.ai (ML Experiment Tracking) MCP

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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Neptune.ai (ML Experiment Tracking) payment history." If connected, Cascade will call the Neptune.ai (ML Experiment Tracking) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

You configure the server inside your Windsurf MCP settings file. Once active, Cascade can call the server tools autonomously to fetch metadata, search runs, and verify project details.

Yes. Cascade can run `list_models` and compare different iterations in the background while you write code, alerting you if parameters mismatch.

No. The Windsurf agent uses the server tools directly to fetch your run details and project configurations, removing the need for throwaway script writing.

The server uses your standard Neptune API token. Vinkius manages the credential securely, allowing Cascade to execute tools like `list_projects` on your behalf.

This server only reads your ML experiment metadata, run parameters, and model registry details. It does not touch your training datasets or local source code, and Vinkius runs the connection in an isolated sandbox.

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