Claude resources tagged “observability”
50 curated Claude Code resources tagged observability in the HeyClaude directory — mostly mcp servers, tools, and guides. 2 of them sit in the trusted tier.
Highlights from this set
Standout entries tagged observability, picked by their own metadata — trust tier, provenance, documentation, and recency.
All observability resources
Add Observability to LLM and Agent Applications
Instrument LLM and agent apps with traces, metrics, logs, and redaction.
Agent Observability SRE Agent
Operate Claude Code agent platforms using official analytics and on-call runbooks.
Agentgateway MCP Gateway
Put agentgateway in front of MCP tools to aggregate multiple targets, proxy remote servers, spawn stdio servers, serve Streamable HTTP and SSE endpoints, and add auth, policy, telemetry, guardrails, and Kubernetes-native routing.
AgentOps
Open-source observability for AI agent traces, replays, and costs.
Agno
Build and run agent platforms with agents, teams, workflows, memory, MCP, and AgentOS.
AI Agent Observability and Incident Response Skill
Add actionable observability for prompts, tools, latency, failures, and safety events with incident response runbooks.
Archestra MCP Platform
Self-host Archestra to curate approved MCP servers, run self-hosted MCP servers in Kubernetes, expose curated MCP gateway endpoints to clients such as Claude, and apply auth, access control, observability, and tool-use policies.
Arize Phoenix
Open-source LLM observability and evaluation tooling.
AWS CloudWatch MCP Server
Connect Claude to Amazon CloudWatch to query metrics, inspect alarms, analyze logs, and run PromQL for AI-assisted incident troubleshooting.
Axiom MCP Server for Claude
Official Axiom MCP: APL queries, dashboards & monitoring from Claude.
Build Cloudflare Workers AI Agents With Durable State
Build Workers AI agents with durable session and workflow state.
CircleCI MCP Server
CircleCI's official Model Context Protocol server exposing 18 tools to inspect build failures, flaky tests, pipeline status, logs, and config validation from any MCP-compatible client.
Claude Agent SDK OpenTelemetry Observability Capability Pack Skill
Configure Agent SDK OTLP telemetry with documented env vars and privacy review matrices.
Cost Tracking for Claude Agent SDK Applications
Read total_cost_usd from the result message, dedupe parallel tool calls by id, split spend per model, and track cache token fields.
Dagster
Orchestrate data assets, pipelines, jobs, schedules, sensors, and observability.
Datadog MCP Server for Claude
Connect Claude to Datadog telemetry, incidents, monitors, dashboards, logs, traces, metrics, services, and tool-call audit data.
Dynatrace MCP Server for Claude
Official Dynatrace MCP: DQL queries, problem investigation & entity analysis from Claude.
Elasticsearch MCP Server for Claude
Elastic's official MCP server: query Elasticsearch indices, mappings, and ES|QL from Claude.
Evidently
Evaluate, test, and monitor ML models, LLM apps, data quality, and drift.
Grafana MCP Server for Claude
MCP server for querying Grafana metrics and logs, inspecting dashboards, managing alerting, and generating Grafana deeplinks.
Honeycomb MCP Server for Claude
Official Honeycomb MCP: query traces, investigate alerts & manage SLOs from Claude.
IBM MCP Context Forge
Run ContextForge as a Python or containerized MCP gateway, register downstream tools and virtual servers, bridge HTTP/SSE services into stdio clients with mcpgateway.wrapper, and manage auth, policies, logs, and tracing centrally.
Incident Timeline Reconstruction Capability Pack Skill
Reconstruct production incident timelines from logs, traces, deploy events, and alerts with source-backed correlation and privacy-safe output.
InfluxDB 3 MCP Server
Official InfluxDB 3 MCP server: run SQL, write line protocol, inspect schema, and manage databases and tokens across Core, Enterprise, and Cloud.
Laminar
Open-source AI-agent observability with tracing, evals, signals, SQL dashboards, and datasets.
Langfuse Docs MCP Server for Claude
Public Langfuse Docs MCP server for agent-ready documentation search, page retrieval, and implementation guidance over Langfuse observability docs.
LangSmith
Observability and evaluation platform for LLM apps.
LangSmith MCP Server for Claude
Official LangSmith MCP: traces, prompts, datasets & experiments from Claude.
Live Incident Debugging Triage Agent
Triage live production outages with impact framing, evidence timelines, logs, traces, dashboards, rollback options, and safe recommendations.
Log Parsing + Incident Timeline Skill
Parse web, application, and system logs into structured incidents and timelines with anomaly detection.
MLflow
Trace, evaluate, monitor, and manage agents, LLM apps, prompts, and models.
New Relic MCP Server for Claude
Connect Claude to New Relic entities, alerts, NRQL, incidents, logs, dashboards, performance analytics, and deployment impact tools.
OpenSearch MCP Server
Official OpenSearch MCP server: list indices, read mappings, run Query DSL/PPL searches, and inspect shards and cluster health over stdio or streaming.
OpenTelemetry MCP Server for Claude
OpenTelemetry MCP: search traces, find errors, analyze LLM token usage & discover AI model patterns.
OpenTelemetry Observability for Claude Agent SDK Agents
Export OpenTelemetry traces, metrics, and events from the Claude Agent SDK with OTLP, and control what content is exported.
OpenTelemetry Trace Analysis Agent
Analyze OpenTelemetry traces for agent workloads using official trace signal docs.
Portkey AI Gateway
Open-source AI gateway to 1600+ LLMs with retries, fallbacks, routing, guardrails, caching, and observability.
PostHog MCP Server for Claude
Official PostHog MCP server for asking Claude to query and manage PostHog projects through a scoped personal API key.
Production Reliability Engineer - Agents
Ensure production deployment reliability with SRE best practices.
Prometheus MCP Server
Connect Claude directly to Prometheus metrics with Docker, Helm, auth, query-timeout, and tool-prefix configuration.
Pydantic Logfire MCP Server for Claude
Official Logfire MCP: query OTel traces, manage dashboards & analyze exceptions from Claude.
SaaS MCP Starter Pack
MCP starter bundle for SaaS builders connecting code, data, billing, deployments, issues, and observability.
Strands Agents
Python and TypeScript agent SDK with model providers, MCP, streaming, structured output, hooks, observability, tools, and multi-agent patterns.
Structured Logging Review Rules
Review logging changes for structured events, consistent levels, correlation IDs, actionable messages, volume control, and no secrets or personal data.
TruLens
Evaluate and trace agents, RAG systems, LLM apps, metrics, and regressions.
VoltAgent
TypeScript agent framework with workflows, MCP tools, memory, RAG, guardrails, evals, voice, and VoltOps observability.
Signal coverage
How these 50 resources score on the trust and safety signals HeyClaude reviews — counted from this set, not the directory as a whole.
A short, calm digest of reviewed Claude resources. Unsubscribe any time.