How to Use the Netdata MCP in Cursor

Q: Can I use Cursor to debug a specific Netdata node?

Yes. Your agent runs listspacenodes to find the target machine, then uses getalarms to pull its active warnings. You can troubleshoot the node directly from your editor sidebar.

Q: Does the Netdata integration in Cursor support custom charts?

Yes. The agent runs listcharts to discover all charts, including custom ones you configured. It then uses getchartdata to pull the specific metrics into your workspace.

Q: How does the agent handle large metric payloads?

To avoid cluttering your context window, the agent uses getchartdata with specific time ranges. It avoids running getallmetrics unless you explicitly ask for a full telemetry dump.

Inspect live Netdata metrics and alarms directly inside Cursor to write code that reacts to real-time system performance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Netdata MCP to Cursor

Create your Vinkius account to connect Netdata 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 Netdata with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live context injection for system code

The `get_agent_info` tool pulls live system metadata directly into your Cursor editor. Your agent uses this data to write configuration scripts or deployment code that matches your actual hardware specs. No more hardcoding values or guessing system limits. While you write code, Cursor queries `list_charts` to check which metrics are available on your target nodes. It adapts your monitoring scripts on the fly based on the real metrics your system exports.

Automated alert triage with this MCP Server

The `get_alarms` tool retrieves the active status of every configured alarm on your system. When a test fails or a local deployment breaks, your agent checks these alarms to see if CPU or memory limits caused the crash. You get the root cause without leaving your code. This MCP Server feeds live error states directly into your chat. Your agent correlates the code you just wrote with active alerts from `list_space_alerts` to find regressions instantly.

Time-series data inside your editor

The `get_chart_data` tool fetches raw performance statistics for any chart on your node. Your agent uses this data to analyze resource consumption trends during local test runs. You see exactly how your code changes affect system memory or disk I/O. Cursor displays this data directly in your active terminal or chat panel. By calling `get_all_metrics`, your agent verifies that your application exports the correct telemetry before you push to production.

Setup guide

Set up Netdata 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 Netdata 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 Netdata transactions." If the MCP tools are loaded correctly, Cursor will call the Netdata tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "netdata-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 Netdata. 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 Netdata 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 Netdata MCP in Cursor

Add the server to your cursor configuration file under the mcpServers key. Once configured, enable Agent mode in the Cursor chat to let the editor call the infrastructure tools.

Yes. Your agent runs `list_space_nodes` to find the target machine, then uses `get_alarms` to pull its active warnings. You can troubleshoot the node directly from your editor sidebar.

Yes. The agent runs `list_charts` to discover all charts, including custom ones you configured. It then uses `get_chart_data` to pull the specific metrics into your workspace.

To avoid cluttering your context window, the agent uses `get_chart_data` with specific time ranges. It avoids running `get_all_metrics` unless you explicitly ask for a full telemetry dump.

Your raw metrics and alert configurations are processed locally by the editor. This MCP server communicates directly with the Netdata API using your local tokens, ensuring your performance data is never stored on external indexing servers.

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