67 tagged observability, measured the same way as everything else here.
Browse within: model-context-protocol 15monitoring 10llm-agents 5opentelemetry 5
MCP server Claude CodeCodexCursor
MCP server "aisentinel" as configured in Kabzhanov/AISentinel. Launched with https://github.com/Kabzhanov/AISentinel/releases/download/v1.0.6/aisentinel-v1.0.
MCP server Claude CodeCodexCursor
Flight recorder for AI agents: tamper-evident audit logging, policy enforcement, and incident reports. Runs locally from the aileron Python package.
capabilityhostprotocol/chp-core
MCP server Claude CodeCodexCursor
Learn and adopt the Capability Host Protocol — the agentic web's open evidence layer. Remote server at capabilityhostprotocol.com.
MCP server Claude CodeCodexCursor
One of 2 in server.json
Vantio Gate — Policy Latch dry-run evaluate for agents. No live enforce from MCP. Runs locally from the @vantio/gate-mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor
One of 2 in server.json
Vantio Optics — read-only Sight Loop observe for agents. Proofs, hosts, upgrade path. Runs locally from the @vantio/optics-mcp npm package.
MCP server Claude CodeCodexCursor
MCP server "observability-mcp" as configured in sandraschi/observability-mcp. Runs locally from the observability-mcp Python package.
MCP server Claude CodeCodexCursor
Syncause Debug MCP Server. Runs locally from the @syncause/debug-mcp npm package.
MCP server Claude CodeCodexCursor
MCP server that routes LLM calls through CLI subscriptions (Claude, Gemini, Codex, Copilot). Runs locally from the mcp-llm-bridge npm package.
MCP server Claude CodeCodexCursor
MCP server "devcontext" as configured in sid-stack001/devcontext. Runs f:\project\devcontext\server.py with python.
MCP server Claude CodeCodexCursor
Standalone agent health monitor — detect loops, stuck states, thrash, and runaway costs in any AI agent workflow. Runs locally from the agent-vitals Python package.
MCP server Claude CodeCodexCursor
Uptime, API and server monitoring with outages, reporting, on-call and status pages. Remote server at api.hyperping.io.
MCP server Claude CodeCodexCursor
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first. Runs locally from the agent-obs npm package.
MCP server Claude CodeCodexCursor
Apache Kafka monitoring & management for AI agents (with consumer lag) — governed. Runs locally from the @dockndevai/mcp-kafka npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor
Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside. Runs locally from the hscope npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor
LGTM Observability and Alertmanager MCP Server for Agentic AI! Runs locally from the lgtm-mcp Python package.
telemetryflow/telemetryflow-python-mcp
MCP server Claude CodeCodexCursor
TelemetryFlow Python MCP Server - AI Integration Layer for TelemetryFlow Platform. Runs locally from the telemetryflow-python-mcp Python package.
MCP server Claude CodeCodexCursor
Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible. Runs locally from the ezstat-mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor
Analyze JVM thread dumps with ThreadMine: deadlocks, CPU spikes, pool exhaustion, health score. Runs locally from the @threadmine/mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor
Checks whether an agent trace contains the evidence a post-hoc causal reconstruction would require. Verifies evidence is PRESENT, not that it is true: a fabricated-but-internally-consistent trace passes. Runs locally from the evidence-readiness Python package.
HanbeenMoon/agent-failure-archive
MCP server Claude CodeCodexCursor
186 real AI agent post-mortems, 107 of them measurement failures. Free tools, paid via x402. Remote server at desktop-ai2ata5-1.tailfeb765.ts.net.
MCP server Claude CodeCodexCursor
Read-only ops/health MCP server for a local vLLM server (WSL2/systemd-managed): liveness vs real-completion health tiers, GPU/VRAM status, systemd service status, and live serve-flag introspection. No lifecycle-control tools in this release. Runs locally from the vllm-ops-mcp Python package.
MCP server Claude CodeCodexCursor
MQ-Sentinel — production-grade, read-only IBM MQ diagnostic MCP server for AI agents. Zero hallucinations. Built for trust in enterprise environments. Runs locally from the mq-sentinel Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Sandboxed AI-native bash with 70 agentic tools: runbash, code edit/diff, WASM Python/JS. Runs locally from the @ag-bash/mcp-server npm package.
MCP server Claude CodeCodexCursor
Observatory of public media reception: classify YouTube comments for mood, support and controversy. Remote server at pjq.life.