- Zabbix MCP @mhajder/zabbix-mcpMCP server for Zabbix monitoring and automation4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.10 GitHub stars.
- Safe SSH @areso/safe-ssh-mcpA secured scoped SSH MCP server for executing safe read-only diagnostic DevOps / SysOps commands8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- Observability @thotischner/observability-mcpUnified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- DebugBundle @debugbundle/mcpDebugBundle MCP: runtime error reporting, incident response, health checks, and product analytics.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Tokenectomy Razor @tokenectomy-labs/razorCut 95% of framework noise and token bloat from error logs for AI agents.17% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Tokenectomy Razor @daffa2555/razorAutonomous log surgery & secret redaction MCP server for AI coding agents.16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.6 GitHub stars.
- Fanout @labstack/fanoutInvestigate OpenTelemetry traces, metrics, and logs, and manage personal dashboards.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.6 GitHub stars.
- SSH MCP Server @hypnosis/ssh-mcp-serverModern SSH for AI agents — cloud servers to BusyBox routers, with destructive commands blocked.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Rlg @sebastienrousseau/rlg-mcpMCP server exposing rlg log streams to LLM agents via JSON-RPC 2.0 over stdio.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.6 GitHub stars.
- Datadog @tantiope/datadog-mcpFull Datadog API access: monitors, logs, metrics, traces, dashboards, and observability tools4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Kubeview @mikhae1/kubeviewRead-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Logmcp @kascada/logmcpMCP server — read-only log access for AI assistants, without giving AI shell access.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.5 GitHub stars.
- Log Analyzer @fato07/log-analyzer-mcpAI-powered log analysis - parse, search, extract errors across 9+ formats5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Datto RMM @wyre-ai/datto-rmm-mcpMCP server for Datto RMM — devices, alerts, sites, jobs, and audit data.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.4 GitHub stars.
- Jira Alerts (JSM Operations) @rrvrs/jira-alerts-mcpMCP server for Jira Service Management Operations — alerts, on-call schedules and responders4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Parseable @parseablehq/parseable-mcp-serverModel Context Protocol server for Parseable. Lets LLMs discover and query Parseable.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Runframe @runframe/runframe-mcp-serverMCP server for Runframe incident management covering incidents, on-call, postmortems, and more.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Docker MCP Server @friendlygeorge/docker-mcp-serverMCP server for Docker — containers, health checks, Compose, logs, monitoring for AI agents9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Talos Linux MCP Server @nosmoht/talos-mcp-serverMCP server for Talos Linux — resources, services, logs, health, config, lifecycle via gRPC.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Tideways @abuhamza/tideways-mcp-serverRead-only access to Tideways PHP performance monitoring: performance, issues, traces, history.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Cortex @tootie/cortexSyslog receiver and MCP server for homelab log intelligence.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- Syslog MCP @tootie/syslog-mcpSyslog receiver and MCP server for homelab log intelligence.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- Causely @causely/causelyCausal reasoning for reliability: root cause, blast radius, and service health for agents.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- TacticalRMM @shin2344234/trmm-mcpRead your TacticalRMM fleet; run commands only after per-command human approval.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
