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

Q: How do I install the Neptune.ai (ML Experiment Tracking) MCP Server for Claude Code?

Run the claude mcp add command with the server HTTP transport URL. Once added, the CLI client automatically registers the tools for your terminal sessions.

Q: Can I pipe run data from Claude Code to other terminal utilities?

Yes. You can ask Claude Code to run searchruns and format the output as JSON, which you can then pipe to standard utilities like jq.

Query Neptune.ai (ML Experiment Tracking) runs and models directly from your terminal using Claude Code commands.

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 Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query training metrics from your terminal

Searching active experiments with `search_runs` lets you query training metrics directly from your command line. This MCP Server lets you search your active experiments right from your shell. You can pipe the output of your queries to grep or jq to filter specific metrics. Your agent can quickly pull the latest loss values without loading a heavy web page.

Inspect model versions inside your CLI

Listing registered weights with `list_models` simplifies model auditing inside your terminal session. Claude Code uses this tool to list all registered versions within a project. Once you locate the correct version, the tool uses `get_attributes` to dump the parameters directly to stdout. It makes auditing model configurations fast and scriptable.

Audit workspaces using the Claude Code MCP Server

The Neptune.ai (ML Experiment Tracking) MCP Server lets you audit projects and verify workspace targets before running scripts. The agent uses `list_projects` to verify your available workspaces before initiating queries. If you need specific details about a target, `get_project` fetches the project metadata instantly. It keeps your terminal-based workflows accurate and error-free.

Setup guide

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

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see neptuneai-ml-experiment-tracking-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Neptune.ai (ML Experiment Tracking) transactions." It will automatically discover and invoke the available Neptune.ai (ML Experiment Tracking) tools.

Terminal

claude mcp add --transport http neptuneai-ml-experiment-tracking-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "neptuneai-ml-experiment-tracking-mcp": {
      "type": "url",
      "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 Code

Run the `claude mcp add` command with the server HTTP transport URL. Once added, the CLI client automatically registers the tools for your terminal sessions.

Yes. You can ask Claude Code to run `search_runs` and format the output as JSON, which you can then pipe to standard utilities like jq.

Yes. You can run query commands headlessly, allowing your terminal agent to fetch run attributes using `get_attributes` as part of your shell scripts.

The server uses your standard Neptune API token. Vinkius manages the credential securely, allowing the CLI tool to call `get_user` and verify your permissions.

The integration only accesses ML experiment run parameters, model names, and workspace metadata. Your actual training data and code files are never transmitted, and Vinkius isolates all execution.

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