Can I see the accuracy metrics for a specific ML run through my agent?

Yes. Use the `get_attributes` tool with your Project ID and Run ID. Your agent will retrieve the detailed telemetry logged during that execution, including accuracy, loss, and any custom attributes defined in your code.

How do I check which model versions are currently stable in my registry?

The `list_models` tool retrieves all packaged ML models within a project. Your agent will expose the promoted model versions, helping you distinguish between experimental runs and stable candidates ready for deployment.

Can my agent search through hundreds of past ML experimentation runs?

Absolutely. Use the `search_runs` tool with your Project ID. Your agent will query Neptune's tracking server to identify historical experiment state checkpoints, making it easy to locate specific training results across your entire research timeline.

Neptune.ai (ML Experiment Tracking) MCP Server for Cursor 6 tools — connect in under 2 minutes

Name: Neptune.ai (ML Experiment Tracking)
Availability: InStock
Author: Vinkius

docs.cursor.com/context/model-context-protocol

Built by Vinkius GDPR 6 Tools IDE

Cursor is an AI-first code editor built on VS Code that integrates LLM-powered coding assistance directly into the development workflow. Its Agent mode enables autonomous multi-step coding tasks, and MCP support lets agents access external data sources and APIs during code generation.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

RecommendedModern Approach — Zero Configuration

Vinkius Desktop App

The modern way to manage MCP Servers — no config files, no terminal commands. Install Neptune.ai (ML Experiment Tracking) and 2,500+ MCP Servers from a single visual interface.

Download Free Open SourceNo signup required

Classic Setup·json

{
  "mcpServers": {
    "neptuneai-ml-experiment-tracking": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Neptune.ai (ML Experiment Tracking) MCP Server

Connect your Neptune.ai account to any AI agent and take full control of your machine learning experimentation, model versioning, and training telemetry through natural conversation.

Cursor's Agent mode turns Neptune.ai (ML Experiment Tracking) into an in-editor superpower. Ask Cursor to generate code using live data from Neptune.ai (ML Experiment Tracking) and it fetches, processes, and writes. all in a single agentic loop. 6 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.

What you can do

Experiment Orchestration — List all managed ML projects and retrieve detailed metadata configurations tracking active runs and workspace boundaries directly from your agent
Run Audit & Search — Discover specific training runs or historical experiment state checkpoints mapping deep ML parameter sets and performance bounds securely
Attribute Inspection — Extract detailed telemetry capturing the exact variables, accuracy metrics, and loss curves logged during specific execution checkpoints natively
Model Registry Management — List and retrieve trained tracking models promoted and logged explicitly, isolating stable versions from ephemeral experimentation runs
Organizational Visibility — Enumerate accessible workspaces and projects to understand your ML research footprint and documentation distribution natively
Credential Audit — Verify specific user identifies and availability details bound inherently against your active service account token securely
Metadata Retrieval — Deep-dive into specific Project or Run IDs to retrieve precise JSON representations and chronological experimentation insights instantly

The Neptune.ai (ML Experiment Tracking) MCP Server exposes 6 tools through the Vinkius. Connect it to Cursor in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Neptune.ai (ML Experiment Tracking) to Cursor via MCP

Follow these steps to integrate the Neptune.ai (ML Experiment Tracking) MCP Server with Cursor.

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"

Add the server config

Paste the JSON configuration above into the mcp.json file that opens

Save the file

Cursor will automatically detect the new MCP server

Start using Neptune.ai (ML Experiment Tracking)

Open Agent mode in chat and ask: "Using Neptune.ai (ML Experiment Tracking), help me...". 6 tools available

Why Use Cursor with the Neptune.ai (ML Experiment Tracking) MCP Server

Cursor AI Code Editor provides unique advantages when paired with Neptune.ai (ML Experiment Tracking) through the Model Context Protocol.

Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context

Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards

MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment

VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools

Neptune.ai (ML Experiment Tracking) + Cursor Use Cases

Practical scenarios where Cursor combined with the Neptune.ai (ML Experiment Tracking) MCP Server delivers measurable value.

Code generation with live data: ask Cursor to generate a security report module using live DNS and subdomain data fetched through MCP

Automated documentation: have Cursor query your API's tool schemas and generate TypeScript interfaces or OpenAPI specs automatically

Infrastructure-as-code: Cursor can fetch domain configurations and generate corresponding Terraform or CloudFormation templates

Test scaffolding: ask Cursor to pull real API responses via MCP and generate unit test fixtures from actual data

Neptune.ai (ML Experiment Tracking) MCP Tools for Cursor (6)

These 6 tools become available when you connect Neptune.ai (ML Experiment Tracking) to Cursor via MCP:

get_attributes

Get parameters mapped within an experiment runtime bounds

get_project

Get specific details for a targeted Neptune ML project

get_user

Get specific user credentials and availability details

list_models

List trained tracking models packaged natively within a project

list_projects

List accessible Neptune workspaces and projects

search_runs

Search explicitly tracked ML experimentation runs inside a project

Example Prompts for Neptune.ai (ML Experiment Tracking) in Cursor

Ready-to-use prompts you can give your Cursor agent to start working with Neptune.ai (ML Experiment Tracking) immediately.

"List all training runs for the 'Customer-Churn' project"

"Show me the metrics for run ID 'churn-exp-123'"

"List all registered models in project 'Fraud-Detection'"

Troubleshooting Neptune.ai (ML Experiment Tracking) MCP Server with Cursor

Common issues when connecting Neptune.ai (ML Experiment Tracking) to Cursor through the Vinkius, and how to resolve them.

Tools not appearing in Cursor

Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.

Server shows as disconnected

Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.

Neptune.ai (ML Experiment Tracking) + Cursor FAQ

Common questions about integrating Neptune.ai (ML Experiment Tracking) MCP Server with Cursor.

What is Agent mode and why does it matter for MCP?

Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.

Where does Cursor store MCP configuration?

Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.

Can Cursor use MCP tools in inline edits?

No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.

How do I verify MCP tools are loaded?

Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.