"A non-coding Claude MCP server" matching MCP servers:

An MCP server for querying Grafana Loki directly with a discovery-first workflow — labels, values, series, and LogQL queries without requiring Grafana.

MCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.

Model Context Protocol (MCP) server for debugging, analyzing, and diagnosing Kubernetes clusters directly from AI agents.

16-tool MCP server for Google PageSpeed Insights & Chrome UX Report APIs. Analyze, compare, and optimize web performance directly through Claude, Cursor, or any MCP-compatible AI client.

Uptime monitoring for websites, APIs, SSL certificates, domain expiry, ping and TCP/UDP ports. 15 tools to list, create, pause and delete monitors, pull incident timelines with error codes, and read hourly or daily uptime and response-time statistics.

MCP server for managing Ubuntu servers over SSH. Enables Claude to check system health, inspect services, tail logs, review updates, and run commands remotely.

Model Context Protocol server for Verlon AI that exposes gates, logs, recommendations, and experiments as MCP tools, enabling coding agents to inspect and manage AI infrastructure natively.

MCP server that provides read-only analysis of Claude Code session transcripts, enabling queries about project activity, session details, and tool usage.

Exposes an observability REST API as MCP tools, enabling incident investigation through automated correlation of deploys with errors, log and metrics queries.

Read-only AMD GPU monitoring for Claude on Linux — VRAM, temperature, clocks, power, and running ML processes via rocm-smi.

Enables Claude to discover and understand infrastructure-as-code drift by listing projects with drift, analyzing Terraform plan outputs, and providing remediation information.

Provides read-only access to host system metrics (CPU, memory, disk), Docker container health/logs, and sandboxed log file analysis via MCP tools, enabling AI agents to monitor enterprise infrastructure safely.

MCP server enabling AI assistants to interact with your LogicMonitor, providing 125 tools for comprehensive monitoring and management operations.

An MCP server that enables natural language querying and troubleshooting of Kubernetes clusters, supporting multi-cluster switching and providing tools for pods, nodes, events, and logs.

Official MCP server for the openITCOCKPIT monitoring platform: host and service state, check and state history, log entries, downtimes, acknowledgements, software inventory and pending security updates.

A read-only MCP server for the Pirsch Analytics API that lets users list domains and query traffic, pages, events, and other analytics metrics through conversational agents.

Enables managing Uptime Kuma monitoring through natural language, including creating, editing, pausing, and deleting monitors, plus retrieving heartbeats, status, metrics, notifications, and status pages.

An instrumented MCP server for debugging lost tool calls in Claude Desktop, using ping, echo, sized_echo, and slow_echo tools to record and analyze the full protocol flow.

Enables AI agents to push and read metrics from EzStat, track counters/gauges, and ask natural-language questions about telemetry.

An MCP server that gives Claude read access to Umami web analytics, allowing natural language queries for stats, breakdowns, pageview trends, live visitors, and user journeys.