Monitoring MCP Server

Netdata

Name: Netdata
Author: netdata

Discovery, exploration, reporting and root cause analysis using all observability data, including metrics, logs, systems, containers, processes, and network connections

Scan flagged something by netdataOfficial78,081GPL-3.0CIntermediatestdiostreamable-http

View on GitHub Install Guide

Install

No auto-install command available for this server.

Check the GitHub repository for setup instructions

Remote Endpoint Available

This server offers a hosted endpoint — no local installation required.

https://app.netdata.cloud/api/v1/mcp

Safety Report

67% Scan flagged something

Scanned 5 months ago

4 passed 2 warnings

Security

Authentication

details

Authentication detected: env_api_key_py, env_required, auth_header, oauth

Pass

CORS Policy

details

No CORS-relevant transport detected (likely stdio)

N/A

Rate Limiting

details

No rate limiting mechanism detected

Info

Known CVEs

details

No known CVEs in dependencies

Pass

Code Quality

Dependency Audit

details

No known vulnerable dependencies detected

Pass

Dangerous Patterns

details

Dangerous patterns detected: eval_call

Warning

License

details

License: GPL-3.0

Pass

Community

Maintenance Status

details

Last commit 5 months ago

Warning

Learn about our security methodology →

Compatibility

Claude Desktop

Not Tested

Claude Code

Not Tested

Cursor

Not Tested

VS Code

Not Tested

Tools Provided (10)

get_nodes

Discover all connected Netdata nodes with hardware specs, OS details, and virtualization information.

get_metrics

Query time-series metrics with grouping and aggregation options across all collected system, application, and hardware metrics.

get_anomalies

ML-powered anomaly detection across all metrics for a given node or time range.

get_correlations

Correlation analysis to identify metric changes and causal relationships during incidents.

get_alerts

Retrieve active alerts with full state tracking, history, thresholds, and recipient metadata.

get_processes

Live process details including CPU, memory, I/O, and file descriptor usage (requires API key + claimed agent).

get_connections

Active network connections with protocol details, states, addresses, and ports (requires API key + claimed agent).

get_systemd_services

List and query systemd service and unit states (requires API key + claimed agent).

get_logs

Query systemd-journal or Windows event logs with filtering and full-text search (requires API key + claimed agent).

get_containers

List running containers, VMs, mount points, block devices, and network interfaces on a node.

Frequently Asked Questions

What is Netdata?

Discovery, exploration, reporting and root cause analysis using all observability data, including metrics, logs, systems, containers, processes, and network connections

What tools does Netdata provide?

Netdata provides 10 tools including get_nodes, get_metrics, get_anomalies, get_correlations. Each tool can be called by AI agents to perform specific operations.

Is Netdata safe to use?

We cannot tell you that, and nobody scanning at this scale can. What we did in March 2026 was shallow-clone Netdata and run five keyword searches over its source: auth identifiers, CORS configuration, rate-limit identifiers, the dependency manifest against a hardcoded list of 18 known-vulnerable packages, and unguarded eval/exec calls. At least one matched — the specific finding is in the scan report on this page. A text search cannot follow a variable, judge intent, or tell you what a server does once it is running, so "nothing matched" is not "safe". What the scan does and does not cover is written out at /mcp/security.

What are alternatives to Netdata?

Similar MCP servers include MCP Grafana, Zabbix MCP Server, Logfire MCP. Each serves a similar purpose but may differ in features, language, and compatibility.