How to Use the Neptune.ai (ML Experiment Tracking) MCP in VS Code Copilot

Q: Can VS Code Copilot check model registry stages from Neptune.ai (ML Experiment Tracking)?

Yes, your agent uses the listmodels tool to fetch the registry. You can check if a model version is ready for staging directly within your editor.

Q: How do I pull run parameters into VS Code Copilot from Neptune.ai (ML Experiment Tracking)?

Your agent invokes the getattributes tool to fetch the logged parameters. It then inserts those values directly into your active workspace or chat discussion.

Q: Can I see who logged a specific experiment?

Yes, the getuser tool retrieves details about the user associated with specific credentials. This helps you trace who ran a particular set of trials.

Share Neptune.ai (ML Experiment Tracking) context across your team using VS Code Copilot agent tools powered by 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 VS Code Copilot

Create your Vinkius account to connect Neptune.ai (ML Experiment Tracking) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query training runs inside VS Code Copilot

The `search_runs` tool queries your team's shared workspaces to find specific training runs. When debugging a failed model, your Copilot agent uses this tool to pull the exact run parameters and loss curves into your chat panel. This MCP capability helps teams diagnose training anomalies without sharing screenshots of web dashboards. Every developer can query the same run metadata using natural language queries.

Validate model parameters using this MCP Server

The `get_attributes` tool retrieves the logged parameters and metrics from any historical experiment. Your agent uses this tool to verify that your local inference script matches the exact configuration of the trained model. It prevents deployment mismatches by pulling the actual logged dictionary keys. You can instantly confirm if a feature flag or preprocessing step was active during training.

Map workspace projects in VS Code Copilot

The `list_projects` tool retrieves all accessible Neptune workspaces and projects for your team. Your agent uses this list to verify project names and configure workspace scopes across shared repositories. It works alongside `get_project` to ensure your team's workspace configurations stay synced. This keeps everyone querying the correct project directories during collaborative debugging sessions.

Setup guide

Set up Neptune.ai (ML Experiment Tracking) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Neptune.ai (ML Experiment Tracking) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Neptune.ai (ML Experiment Tracking) tools listed. Try asking: "List my recent Neptune.ai (ML Experiment Tracking) transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

You commit the server config to your repo, and your team uses the MCP server tool. This lets everyone query and discuss experiment results in the shared chat.

Yes, your agent uses the `list_models` tool to fetch the registry. You can check if a model version is ready for staging directly within your editor.

Your agent invokes the `get_attributes` tool to fetch the logged parameters. It then inserts those values directly into your active workspace or chat discussion.

Yes, the `get_user` tool retrieves details about the user associated with specific credentials. This helps you trace who ran a particular set of trials.

No, the connection runs through a secure sandbox that keeps your credentials and project metadata private. No run parameters or metrics are cached or sent to external servers, complying with standard enterprise security policies.

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