- Conduid
- Marketplace
- #observability
MCP servers tagged observability
791 live MCP servers tagged "observability", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with observability.
Agentobs
Stop your AI coding agent before it overspends. Budget limits, guardrails and cost tracking for Claude Code - local-first, no account.
Opencode Skill Tracker
📊 OpenCode plugin + TUI that records skill, MCP and plugin tool usage into a local SQLite database — no network, no message bodies.
Pi MCP Viz
Pi extension that visualizes MCP server activity: transcript cards, an auto-dismissing modal and a status-line badge, with a token counter for the documents read by the MCP knowle…
LLM Hops
See every hop of a request through your local LLM system: a tracing server, a live flow map, a waterfall per request, and an MCP server for Claude Code and Cursor. One static Go b…
FaultDebugMCP
Turn C/C++ crashes into source-verified execution-flow reports. Local tracing, cross-service examples, CLI and read-only MCP.
Ican Digital Human Agent
数字人 Agent 底座：Spring Boot 认证网关 + FastAPI/LangGraph 编排 + 混合检索 RAG + MCP 工具 + 实时语音，含离线评测与可观测性
Cortextrace
Local-first desktop observability, tracing and threat detection for AI agents (Claude Code, Cursor, MCP, OpenTelemetry)
Sovereign Projects
Maximal sovereign workspace layer and monorepo
SDK Typescript
🚀 Build efficient applications with the MCP SDK for TypeScript, offering optimized performance, real-time communication, and robust session management.
Scope
A transparent JSON-RPC capture, viewer, and diff tool for the Model Context Protocol
Datadog
📊 Integrate Datadog Logs, Monitors, Metrics, Incidents, and Dashboards with this Model Context Protocol (MCP) server for seamless AI assistance.
Sapmcp
Production-minded MCP server for SAP ECC/S/4HANA over NetWeaver RFC SDK (ctypes, no PyRFC): SafetyPolicy, audit JSONL, Basis tools, multi-destination and snapshots.
Pulse
connect everything. your ai does the rest.
Github Intelligence MCP
An intelligent, structured MCP (Model Context Protocol) server for investigating and analyzing GitHub repositories.
Skills
Honeybadger skills for AI coding agents (Claude Code, Codex, Cursor, and more)
Client
Full-featured Elixir client for the Model Context Protocol (MCP) with multi-transport support, resources, prompts, tools, and telemetry.
Gateway
🔀 A lightweight, open-source gateway for managing, routing, and monitoring multiple MCP (Model Context Protocol) servers. Auth · Rate-limit · Metrics · Tool discovery.
Agentlens
Local-first AI agent debugger: trace waterfalls, LLM cost & token analysis, MCP inspection, retry/loop detection. English / 中文. 开源 AI 智能体调试与可观测性工具。
Ops
Read-only MCP server that gives your AI agent eyes on your whole production stack: Stripe, Postgres, Vercel, Sentry, GitHub and more. Status in one call, a cross-service timeline,…
AgentGuard
Protect AI agents by detecting and blocking prompt, command injection, Unicode bypass, and social engineering attacks with customizable security controls.
Cortex
Archived — AI-powered autonomous DevOps platform with multi-agent orchestration, neural routing, and self-healing infrastructure.
Observability MCP
FastMCP 3.2 observability server for monitoring MCP ecosystems with OTel and Grafana
Ouroboros AI
Self-healing AI agent observability system — SigNoz Observability Hackathon 2026
Server
Syncause runtime facts MCP server
Knowledge Server
Production-oriented MCP-style FastAPI backend with typed tools, API key auth, scopes, audit logs, PostgreSQL search, Redis, metrics and CI.
Db2 MCP Server
Secure, observable Java 21 MCP server for governed read-only AI access to IBM Db2.
Devtools
Chrome DevTools for the Model Context Protocol. Inspect, profile, replay, and diff every MCP call your agent makes.
Rius SDK Typescript
OpenTelemetry-native agent observability: trace every LLM call, tool call and agent step, with cost per call, alerts, and Claude Code / Codex / Cursor session tracing. TypeScript…
Devcontext
An MCP server that gives coding agents live production context (logs, deploys, health) for evidence-based incident diagnosis instead of blind guessing. Format-adaptive log parser…
Mcpgate
Open-source MCP gateway — reverse proxy for Model Context Protocol servers with auth, rate limiting, access control, and observability
Explorer
A local-first, multi-agent query interface built with LangChain, Chainlit, and Ollama, featuring dynamic Model Context Protocol (MCP) tool integration and Langfuse observability.
Mcpbench
MCP server load tester: concurrent JSON-RPC, per-tool p50/p95/p99, stdio+HTTP/SSE transports, CI regression gating
Kpm
🚀 Kubernetes Pods Metrics — sample to SQLite; analyze-local + recommend, capacity/TUI; optional notify/MCP/server charts
Fleetglass
One cockpit for your server and the AI agents running on it. Self-hosted, read-only monitoring that ties every Claude Code and Codex session to CPU, RAM, tokens/s, cost and quotas.
Datadog MCP Server
LLM-optimized MCP server for Datadog APM, logs, and metrics. Delivers structured, token-efficient trace and log insights designed specifically for AI-driven debugging—not just raw…
Azure MCP
MCP server for inspecting Azure API Management, Application Insights and App Service through .NET.
Laravel Kick
🔗 Connect and manage your Laravel app effortlessly with an MCP server and REST API for health checks, log reading, and command execution.
Gt8004 SDK
Official Python SDK for GT8004 — AI agent observability with MCP, A2A, x402 payment tracking. FastAPI, Flask, FastMCP middleware included.
Toad Eye
OpenTelemetry observability for LLM systems — auto-instrumentation (OpenAI, Anthropic, Gemini, Vercel AI SDK), cost tracking, budget guards, agent tracing, OTel GenAI semconv, 8 G…
Netspy
A unified CLI tool that provides both direct network telemetry querying and MCP (Model Context Protocol) server capabilities for real-time network connectivity analytics and AI-po…
Shark Viewer Vscode
MCP Shark Viewer integrates MCP Shark into VS Code/Cursor so you can inspect MCP traffic without leaving your IDE
webaesbyamin/agent-receipts
constraints, chains, AI judgment, invoicing, local dashboard.
Eventloom
Eventloom is a local-first TypeScript runtime for multi-agent systems built around an append-only event log.
Claude Code Lens
Local monitor for Claude Code API traffic, logs, prompts, and tools
Jwrede/llmprobe
Synthetic monitoring for LLM inference endpoints. Measure TTFT, latency, throughput, and errors across OpenAI, Anthropic, Google, Azure, Bedrock, and local servers (vLLM, SGLang,…
Rag Forge
Production-grade RAG pipelines with evaluation baked in
Stoic Agentos
The Operating System for AI Agent Fleets - monitor, orchestrate, and persist knowledge across your AI agents from a single dashboard.
enmanuelmag/heimdall-mcp
mcp`
Spanly
Observability for MCP servers and AI agents. TypeScript SDK, Python SDK, and CLI.
Fascicle
Compose agents like plain values. A TypeScript toolkit that wires LLM calls, tools, and functions into typed steps over eight providers. No framework, no ambient state.