"Observability" matching MCP servers:

A read-only MCP server that exposes Azure incident-investigation tools for a single App Service and its Application Insights telemetry, enabling an agent to correlate deployment history, platform metrics, and transaction traces.

MCP server for AI agent observability, providing trace and span logging, search, latency/tokens/cost metrics, and anomaly detection using an in-memory buffer.

Provides comprehensive monitoring and observability for MCP server ecosystems with real-time health checks, performance metrics, distributed tracing, anomaly detection, and automated performance reports using OpenTelemetry and Prometheus.

A portable, read-only Model Context Protocol server for turning observability data into bounded evidence that AI agents can inspect safely.

A read-only MCP server that enables agents to query and analyze Langfuse observability data, including traces, sessions, observations, scores, and metrics.

An MCP server that gives AI assistants direct access to Kubernetes clusters for pod management and network debugging (DNS, NetworkPolicy, ingress, service mesh) and correlates Dynatrace observability with OpenTelemetry self-monitoring, which automatically ships traces, metrics, and logs to Dynatrace.

An MCP server that exposes RAG search, ServiceNow, and observability tools to MCP clients, and proxies curated calls to remote ServiceNow and observability MCP servers.

8 standalone MCP servers for SMBs — Guardrails (prompt injection, PII, secrets detection), FinOps (AI cost tracking and budgets), Observability (agent tracing), Smart Router (17+ models, 9 providers), Trust Score (governance scoring 0-100), Memory (persistent agent memory), ThinkSecure (runtime security + SOC2/GDPR audit), and A2A Lite (agent-to-agent protocol). 37 tools total, TNC credits

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.

Radar is an open-source Kubernetes observability and diagnostics MCP server. It exposes cluster health, workload diagnosis, logs, events, topology, audit findings, and remediation actions to AI agents through the Model Context Protocol.

Lets AI agents query, manage, and operate their LLM observability data directly from the conversation. Provides 87 tools for cost analysis, alerting, anomaly detection, and runtime control gates.

Enables AI assistants to interact with a Qdrant vector database by exposing collection, point, vector, payload, snapshot, search, recommendation, discovery, and observability operations as MCP tools.

Gives AI assistants read-only access to a Kubernetes cluster's observability stack — Loki, Prometheus, Tempo, the Kubernetes API — plus AWS telemetry from CloudTrail, Config, ECR, and RDS. 23 tools for querying logs, metrics, traces, Kubernetes events, deployments, and audit history in plain language.

Enables AI assistants to access full Datadog observability, including log search, APM trace filtering, smart sampling, and cross-correlation between logs, traces, and metrics.

Bridges AI coding assistants with the OpenTelemetry ecosystem, providing real-time access to repositories, documentation, examples, semantic conventions, and instrumentation scoring for high-quality observability.

Enables AI assistants to interact with self-hosted Dynatrace Managed environments to retrieve observability data, security insights, and performance metrics. It allows users to query problems, logs, events, and SLOs through natural language interfaces in both local and remote modes.

A production-grade, extensible Python template for building Model Context Protocol servers with support for Streamable HTTP and stdio transports. It provides a structured framework for implementing tools, resources, and prompts with built-in authentication, observability, and background task management.

Enables language models to access LangSmith observability platform features including fetching conversation history, managing prompts, retrieving traces and runs, working with datasets and examples, and analyzing experiments.

A production-ready TypeScript template for building MCP servers with dual transport support (stdio/HTTP), OAuth 2.1 foundations, SQLite caching, observability, and security features including PII sanitization and rate limiting.

Provides a suite of utility tools for daily operations, including file format conversion, web page monitoring with change detection, Telegram polls, trading signals from Binance, weather alerts, and more. It includes retry/backoff handling, state persistence, and observability features.

A FastMCP (Python) server for Rocket.Chat with 28 tools covering channels, messages, threads, DMs, files, users, and analytics, plus AI governance, observability, and security features.

BetterDB gives Claude Code, Cursor, Windsurf, and other MCP clients deep observability into Valkey and Redis instances. It implements 22 MCP tools including get_health, get_slowlog, get_commandlog, get_hot_keys, get_anomalies, get_cluster_nodes, get_cluster_slowlog, and get_slot_stats.

A comprehensive gateway and registry that unifies MCP, REST, and Agent-to-Agent services into a single secure endpoint for AI clients. It provides advanced capabilities including federation, virtual servers, rate-limiting, and OpenTelemetry observability.

Game observability and analytics for coding agents: stutters, crashes, custom metrics, dashboards and playtest bots for Unity, Godot, Unreal, Three.js, Phaser and GameMaker games.

Enables AI agents to perform observability analysis across Prometheus-compatible metrics and logs without prior vendor knowledge, including signal discovery, entity topology resolution, root-cause analysis, correlation, and capacity forecasting through natural-language anchors.

Enables MCP-compatible agents to interact with Grafana instances for searching, creating, and updating dashboards, exploring logs via Loki, querying datasources, managing alerts, incidents, and on-call shifts, and accessing observability data.

Maple is a unified MCP server for agent observability, safety control, and behavior evolution, acting as a monitoring and auditing layer for high-agency agents. It enables developers to capture session timelines, replay risky branches, detect anomalies using ML, and enforce action guardrails.

A TypeScript framework for building MCP servers with declarative tool, resource, and prompt definitions, built-in auth, multi-backend storage, and observability.

Enables exposing third-party data sources as Model Context Protocol servers with shared HTTP, rate limits, retries, caching, validation, and observability through thin per-source adapters.

Exposes FastAPI routes as MCP tools with auto-discovery, Pydantic schema extraction, and built-in observability.