Search the catalog, narrow by client, language and transport, and install in one step.
113 servers for “observability”
Governed Prometheus + Grafana ops: PromQL, alerts, dashboards, RCA; 30 tools.
Unified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection.
Agentry skill handoff for agent-native analytics and logging.
Query and analyse your data from Bitmovin Observability
Agent tracing, cost tracking, anomaly detection for LLM agents
AI agent observability with deterministic record/replay for debugging agent failures.
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
Comprehensive MCP server for Grafana, Prometheus, Kafka UI, and Datadog with a secure "Bring Your Own Key" or BYOK model.
Observability for AI agents: 87 tools to query LLM cost, errors, and latency across OpenAI/Anthropic/Gemini/Mistral, and operate alerts, budget gates, evals, and safety checks from Claude/Cursor. Install: npx -y @argosvix/mcp-server.
Read-only Amazon SES observability: search events, inspect bounces, pull delivery stats.
Read-only MCP for AI usage profiles, leaderboards, stats, and docs; no writes or private data.
LLM Observability & Orchestration Agent
LLM Observability & Orchestration Agent (Langchain)
LLM Observability & Orchestration Agent (LangChain Community)
LLM Orchestration Observability Agent
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
AI-powered observability platform for agents. Auto-discovers and recommends MCP servers; built-in connectors for GA4, Vercel, GitHub, and Sentry with ROI tracking. npx -y @perceptdot/core
Multi-agent observability: cascade failure detection, heartbeats, and forensic replay
Governed local-LLM (Ollama) observability: model policy, prompt scanner, 18 tools.
Tamper-evident observability for AI agents: a SHA-256 hash-chained audit log with chain verification and signed export (EU AI Act Art. 12). Instrument any agent with zero code via npx -y @agentlensai/mcp; also ingests OpenTelemetry GenAI traces.
Data observability tools for engineering teams: alerts, freshness, schema drift, lineage, quality.
Persistent agent memory as a single Go binary: knowledge graph, TUI observability, zero infra.
Real-time GitHub Actions observability: DORA Metrics, Cost Analysis, CI/CD Health dashboards.
Structural observability for AI conversations. Detects loops, stuck states, breakthroughs, and convergence across 17 channels without analyzing content.
Datadog observability — 168 tools across metrics, monitors, logs, APM, RUM, incidents, status pages, fleet automation, workflows. 4 workflow Prompts and incident-triage-snapshot aggregation that fans out to 4 fetches in one call.
MCP server providing comprehensive Datadog observability access for AI assistants. Features grep-like log search, APM trace filtering with duration/status/error queries, smart sampling modes for token efficiency, and cross-correlation between logs, traces, and metrics.
Query your Spanlens LLM observability from any MCP client. 7 read tools for request logs, agent traces, cost stats, anomalies, model-savings, and per-user analytics across OpenAI, Anthropic, and Gemini. Open source, self-hostable. npx -y @spanlens/mcp-server
AI-powered SRE observability for Kubernetes and OpenShift with 40+ tools for Tekton pipeline debugging, log analysis, root cause analysis, and predictive monitoring.
A production-grade TypeScript template for scalable MCP servers with built-in observability.
Provides comprehensive integration with your VictoriaLogs instance APIs and documentation for working with logs, investigating and debugging tasks related to your VictoriaLogs instances.
