MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
@jeff-stapleton/observe-mcp-serverupdated this year
MCP server for Observe observability platform integration
npm MIT -
Observability mcp-server for Lockwood Group — hard p99 latency budget under 150ms
-
A comprehensive Kubernetes observability toolkit built on the Model Context Protocol (MCP) for Site Reliability Engineering.
★ 1 -
MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails
npm MIT -
MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails
-
Servidor MCP (Model Context Protocol) en Python para inspeccion y telemetria de Kubernetes, Prometheus y Loki mediante agentes de IA.
MIT -
observe-mcp-servergithub.com/zhangrj/observe-mcp-serverupdated this year
A MCP server that support Prometheus metrics, Openobserve logs and Skywalking traces
GPL-3.0 -
Local runtime observability bridge for AI agents debugging React Native/Expo apps on Android — evidence-first: screenshots, UI trees, per-request network, FPS, React renders, CDP console/heap/profile, deterministic diagnosis, before/after compare.
Apache-2.0 -
Unified observability gateway for AI agents — one MCP server for Prometheus, Loki, and any backend, with cross-signal anomaly detection and a built-in Web UI.
npm Apache-2.0 ★ 7 -
agent-observabilitygithub.com/KryptosAI/agent-observabilityupdated this year
Trace AI agent execution: every tool call, every error, every dollar. Open source agent observability for Claude, Cursor, opencode, and any MCP-compatible agent. Local-first, free forever.
MIT ★ 2 -
Track what every AI coding agent costs and see the limit coming. Per-session, per-model cost for Claude Code, Codex, Cursor and 37 more tools from your provider's own token counts, plus limit gauges, a dangerous-command guard and dashboard terminals. Free, Apache-2.0, runs on your machine.
NOASSERTION ★ 60 -
observer-skillgithub.com/hec-ovi/observer-skillupdated this year
Study a hard video with your coding agent: one Node service transcribes it, serves the player page, and exposes MCP tools so the agent answers at your exact pause point and renders charts it built and verified. Skill plus MCP server, browser TTS and STT.
MIT -
mcp-auditgithub.com/nyx-builds/mcp-auditupdated this year
Agent observability MCP server — trace, audit, and monitor AI agent tool calls. OpenTelemetry, Prometheus, and Grafana export.
-
langfuse-mcpgithub.com/hugoles/langfuse-mcpupdated this year
MCP server that exposes the Langfuse REST API as tools — query traces, observations, sessions, scores, prompts, datasets, and metrics from any MCP client.
npm MIT -
Agent-ready telemetry SDK — enriches OpenTelemetry across Java, Go, Python, Node.js, and browser with structured context for AI-driven observability.
npm Apache-2.0 ★ 11 -
LLM observability and evals in a single binary: traces, prompts, datasets, scores and review queues for LLM and agent apps. Self-hosted, SQLite inside, OpenTelemetry-native, MCP and CLI for coding agents.
Apache-2.0 ★ 1 -
LLMxRay — Local LLM Observatory. Full observability interface for Ollama: chat, streaming, reasoning, RAG, introspection, metrics.
Apache-2.0 ★ 29 -
mcp-k8sgithub.com/krmcbride/mcp-k8supdated this year
Observability focused Kubernetes MCP server
MIT -
mcp-grafanagithub.com/krmcbride/mcp-grafanaupdated this year
Observability focused Grafana MCP server
MIT -
Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.
Apache-2.0 ★ 25 -
Step-by-step observability for MCP agent workflows
npm MIT -
wardgithub.com/useward/wardupdated this year
[WIP] Full-stack observability for Next.js that integrates with your AI coding tools
NOASSERTION -
thehive-cortex-mcpgithub.com/lidless-labs/cortex-mcpupdated this year
Cortex observable-analysis control CLI with an MCP adapter
npm MIT -
Grafana MCP Server with comprehensive API access for dashboards, datasources, alerting, and observability
npm Apache-2.0 -
workflow-studiogithub.com/hculap/workflow-studioupdated this year
Local no-code builder + observability dashboard for Claude Code Workflow multi-agent runs
pypi MIT -
Observe any line of running code — no restarts, no code changes, production-safe
MIT ★ 29 -
@ura-dev/agentracegithub.com/ura-tools/agentraceupdated this year
Structured observability for AI agents — MCP server + CLI viewer
npm MIT -
postgresai – Postgres observability built for humans and AI agents
Apache-2.0 ★ 140 -
Agent observability MCP server for querying OpenTelemetry traces, failures, tool health, security evidence, and regressions.
pypi MIT -
talkops-tempo-mcp-servergithub.com/talkops-ai/talkops-mcpupdated this year
A Model Context Protocol (MCP) server for Grafana Tempo distributed tracing and observability.
pypi Apache-2.0 -
agentwatchgithub.com/nicofains1/agentwatchupdated this year
Multi-agent observability: cascade failure detection, heartbeat monitoring, cross-agent tracing, and forensic replay
MIT ★ 1 -
Runtime observability for AI agents — see exactly what your agent did, why it did it, and what it cost.
pypi MIT -
🤖👁️ 💻 Real-time SSH and shell session observer for Claude Code. Capture at the byte stream, advise without access.
Apache-2.0 -
Local no-code builder + observability dashboard for Claude Code Workflow runs — a Claude Code plugin (uvx workflow-studio).
MIT ★ 3 -
Agent-native observability for NATS and JetStream: web UI, CLI and a read-only MCP server over one bounded query engine.
Apache-2.0 -
Prometheus MCP server — free PromQL metrics store so Claude and ChatGPT can query your observability data
MIT -
mnemogithub.com/ArtLjn/mnemoupdated this year
Structured fact memory MCP server — SQLite + FTS5, trust scoring, entity graph, auto-observe, bilingual retrieval for AI coding assistants
MIT ★ 1 -
Official OutageDeck MCP server for vendor-published cloud and SaaS status, incident timelines, and observed uptime history.
MIT -
Debug Anything: observe and diagnose any running process, container or pod from your agent with one CLI and MCP server. Evidence, not guesses.
npm MIT -
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
MIT ★ 112 -
gasoline-mcpgithub.com/brennhill/gasoline-mcp-ai-devtoolsupdated this year
Gasoline MCP is an AI Debugger, Inspector, and Observability toolkit. It acts as Chrome DevTools for AI Agents using the Model Context Protocol (MCP).
npm AGPL-3.0-only -
Local-first observability and safe recovery for macOS and Windows. See what broke, review the fix, verify the result, and roll back safely.
MIT ★ 2 -
mcp-smb-productsgithub.com/thinkneo-ai/mcp-smb-productsupdated this year
8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.
MIT ★ 1 -
trace-forge-mcpgithub.com/mdfifty50-boop/trace-forge-mcpupdated this year
MCP server for writing structured traces, spans, and decisions — the only write-path observability MCP for EU AI Act traceability compliance
npm MIT -
Universal AI Agent Kernel & Terminal Control Center. Rust-based hardened kernel with Vigils security, real-time observability, and tamper-evident audit ledger.
AGPL-3.0 ★ 2 -
Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.
npm Apache-2.0 ★ 67 -
Agent platform with bitemporal memory, live observability, and audit-grade traceability — for AI that needs to act at the right moment
npm MIT -
Vigilancegithub.com/B-A-M-N/Vigilanceupdated this year
A security minded , realtime AI Intent Observability MCP providing intent tagging and visual mirroring of AI attention to see what context the AI is looking at. Made for visual and coding workflows.
NOASSERTION ★ 1 -
MCP Server for self-improving AI coding skills. Observe → inspect → amend → evaluate loop for SKILL.md files. Works with Claude Code, Codex, and Copilot.
MIT ★ 1 -
MCP server for querying OpenTelemetry traces across multiple observability backends (Jaeger, Tempo, Traceloop, Datadog, and more) for LLM application debugging. Fork of traceloop/opentelemetry-mcp-server.
pypi Apache-2.0 ★ 1 -
iflow-mcp_brennhill-gasoline-agentic-browsergithub.com/brennhill/gasoline-agentic-browser-devtools-mcpupdated this year
Gasoline Agentic Browser is an AI Debugger, Inspector, and Observability toolkit. It acts as Chrome DevTools for AI Agents using the Model Context Protocol (MCP).
pypi AGPL-3.0-only -
@cocaxcode/token-optimizer-mcpgithub.com/cocaxcode/token-optimizer-mcpupdated this year
Orchestration + observability + coach layer for Claude Code token optimization. Measures tool usage, enforces budgets, advises on complementary tools (serena, RTK), and proactively surfaces savings tips.
npm MIT -
OR-Tools optimization service, 11 tools over MCP + REST, with Prometheus/Grafana observability and load tests. Ran in production on Railway Feb-Oct 2026, then shut down to stop costs.
MIT ★ 5 -
Framework-agnostic Java observability sidecar agent: chat with a live JVM via MCP/web UI (metrics, slow calls, errors, logs, thread dumps, method traces). Self-hosted, attachable (Arthas-style). Apache-2.0.
Apache-2.0 ★ 3 -
First-hand observations of public MCP servers: what tools each declared, byte-exactly, and when that declaration changed. Declarations, not behaviour.
-
Debug Anything: observe any running process, container or pod from your AI agent. strace, py-spy, perf, lsof, tcpdump, gdb/lldb and heap snapshots turned into evidence-backed findings. MCP server + CLI.
pypi MIT ★ 14 -
mezmo-mcpgithub.com/mezmo/mezmo-mcpupdated this year
Mezmo MCP: A remote Model Context Provider (MCP) for AI assistants and IDEs to interact with the Mezmo observability platform—enabling pipeline management, log querying, and root-cause analysis via the Model Context Protocol.
★ 8 -
FaceTron is a high-performance face embedding server using ONNX Runtime, supporting dynamic multi-model loading, offline deployment, and scalable environments. It exposes an OpenAPI endpoint with MCP-compatible metadata and integrates with OpenTelemetry for observability.
MIT ★ 5 -
@2kw/ai-mcp-serveractive
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 199 tools for Claude Code, Cursor, and Windsurf.
npm SEE LICENSE IN LICENSE -
An AI agent that trains Earth-observation models on GEO-Bench tasks on its own and carries code-measured lessons from one dataset to the next. Strands + Claude Sonnet on Amazon Bedrock. MCP server designed to plug into GoPilot: pip install gotrain
MIT