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

Q: Can I insert hyperparameters from Neptune.ai (ML Experiment Tracking) directly into my Cursor code?

Yes, your agent uses the getattributes MCP tool to fetch logged parameters. It then writes those exact values directly into your active configuration files inside Cursor.

Q: How does Cursor search my past experiments in Neptune.ai (ML Experiment Tracking)?

Your agent runs the searchruns tool to query your project. It filters the results based on your prompt and displays the matching runs directly in the chat or composer window.

Q: Can I verify model registry states from Neptune.ai (ML Experiment Tracking) inside Cursor?

Yes, the listmodels tool lets your agent pull all registered models. This allows you to check which versions are ready for production without leaving your editor.

Q: How do I know which project the server is querying?

The server uses getproject to target a specific project. You can ask your agent to list all projects first using listprojects to make sure it queries the correct workspace.

Let your Cursor agent pull real Neptune.ai (ML Experiment Tracking) run data directly into your active training scripts using 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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch active run parameters inside Cursor

The `get_attributes` tool pulls specific metrics and parameters mapped within your active experiment runtime bounds. When editing your training loop, your Cursor agent uses this tool to check previous hyperparameter values and insert them directly into your local configuration files. This MCP integration eliminates manual transcription errors when copying learning rates or batch sizes from a web UI. Your agent reads the actual logged values and updates your Python dictionaries in real time.

Pull model registry details into your editor

The `list_models` tool retrieves the registered models packaged natively within your project. Your agent uses this data to write loading scripts that pull the exact model version currently flagged for staging. Instead of guessing model paths, you get the exact string identifiers inserted into your codebase. It ensures your evaluation scripts always point to the correct trained weights.

Filter runs using this Cursor MCP Server

The `search_runs` tool scans your Neptune project to find experiments matching specific performance thresholds. Your agent runs these searches in the background to find which training run achieved the lowest validation loss. Once found, the agent can write a markdown summary of the top five runs directly in your editor. This gives you immediate context on which architectures are performing best without leaving your workspace.

Setup guide

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

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Neptune.ai (ML Experiment Tracking) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Neptune.ai (ML Experiment Tracking) transactions." If the MCP tools are loaded correctly, Cursor will call the Neptune.ai (ML Experiment Tracking) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Yes, your agent uses the `get_attributes` MCP tool to fetch logged parameters. It then writes those exact values directly into your active configuration files inside Cursor.

Your agent runs the `search_runs` tool to query your project. It filters the results based on your prompt and displays the matching runs directly in the chat or composer window.

Yes, the `list_models` tool lets your agent pull all registered models. This allows you to check which versions are ready for production without leaving your editor.

The server uses `get_project` to target a specific project. You can ask your agent to list all projects first using `list_projects` to make sure it queries the correct workspace.

Yes, your credentials and workspace structures are handled locally on your machine. The server communicates directly with the platform's API via secure HTTPS, keeping your proprietary model parameters and metrics completely isolated.

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