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.
-
An open-source, AI-native Model Context Protocol (MCP) server bridging Large Language Models with core network diagnostic tools for automated observability, threat detection, and agentic security orchestration
★ 1 -
omop_mcpgithub.com/OHNLP/omop_mcpupdated this year
Model Context Protocol (MCP) server for mapping clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using Large Language Models
go NOASSERTION ★ 43 -
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.
go Apache-2.0 ★ 1 -
LLMxRay — Local LLM Observatory. Full observability interface for Ollama: chat, streaming, reasoning, RAG, introspection, metrics.
npm Apache-2.0 ★ 29 -
LLM-Powered SRE with A2A Specialists & MCP Observability
-
visantchigithub.com/pedrojaques99/visantchi-cliupdated this year
Local observability CLI for LLM usage — token costs, mascote, MCP server. Offline-first.
npm MIT -
tma1github.com/tma1-ai/tma1active
Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.
Apache-2.0 ★ 125 -
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.
go Apache-2.0 ★ 25 -
ctx-capturegithub.com/sathviknayak123/ctx-captureupdated this year
MCP server for context-window observability: capture and query exactly what an LLM agent saw at every step.
pypi MIT -
AI-powered observability platform using Grafana, Prometheus, MCP and local LLMs for intelligent infrastructure analysis.
MIT ★ 1 -
Observability MCP server for AI agents - 89 tools to query LLM cost/errors/latency across 7 providers and operate alerts, budgets, evals from Claude/Cursor
npm MIT -
Security & Observability for AI Agents — audit every tool call, enforce allow/block policies, catch prompt injection and data leaks. Local-first; works with Claude Code, Codex, Copilot CLI, OpenClaw, LangChain, and all major LLM APIs.
npm NOASSERTION ★ 15 -
Fully local AI stack in Docker Compose — Ollama LLM inference, SearXNG private metasearch, Firecrawl scraping + real browser automation, and Langfuse observability behind one authenticated gateway with an MCP tool interface. No cloud calls, your data stays on your hardware.
MIT -
tokenmarkupdated this year
Drop-in observability and cost tracking for LLM API calls. Wrap your provider client, log every call with cost/tokens/latency to JSONL, query via CLI or MCP.
npm MIT -
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 -
An MCP server that lets an LLM agent query a live Earth Observation catalogue in natural language - eleven typed tools over a production eoAPI stack, zero geospatial code on the client.
Apache-2.0 -
Persistent memory and context-engineering platform for AI agents with memory intelligence, hybrid retrieval, token-budgeted context compilation, custom LLM APIs, MCP, evaluation, observability, and a React control plane.
-
Mnemoscopegithub.com/toonight/Mnemoscopeupdated this year
Observability and predictive memory tooling for LLM agents on Markdown vaults — predictive context-rot scoring, Ed25519-signed hash-chained journal, hierarchical tiering. 100% local. MCP server + Obsidian plugin.
npm Apache-2.0 ★ 1 -
Open-source, self-hosted observability for AI agents: OTLP ingestion, tracing SDK, sessions, cost analytics, datasets and LLM-as-judge experiments, alerts, replay, and an MCP server. SQLite or PostgreSQL.
pypi MIT -
@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 -
Unified LLM gateway with multi-provider routing, caching, MCP server, and observability
MIT -
panoptesgithub.com/sidkos/panoptesupdated this year
Standalone, pluggable observability stack with a read-only MCP interface — one pane of glass across your environments, queryable by both Grafana and LLMs.
Apache-2.0 ★ 1 -
LLM-integrated observability pipeline: ingest kernel/driver hardware diagnostic logs into Elasticsearch, triage failures with a Claude agent over MCP, route deduplicated alerts for scale-out clusters
-
woodpecker-mcpgithub.com/sspcodeflix/woodpecker-mcpupdated this year
MCP server that gives an LLM agent (e.g. HolmesGPT) a materialized, queryable service dependency graph in a graph database - deterministic root-cause (deepest failing service), blast radius, and observability blind-spot detection.
pypi Apache-2.0 -
Anti-confabulation MCP server — verify_claim returns raw observed facts, never verdicts. No API keys, no LLM calls.
MIT ★ 1 -
mcp-server-datadog-forkgithub.com/n1s0-c/mcp-server-datadog-forkupdated this year
MCP server for Datadog with LLM Observability support
Apache-2.0 ★ 1 -
An MCP server that gives LLMs a real interactive PTY with observability and seamless human takeover.
go MIT ★ 14 -
langfuse-mcpgithub.com/dominic-righthere/langfuse-mcpupdated this year
MCP server for Langfuse LLM observability
MIT -
Autonomous LLM cop agent for an inter-group pursuit league: MCP transport, commit-reveal protocol, negotiation playbooks, event-sourced observability, golden-file interop tests.
MIT -
Governed observability + governance for on-endpoint local LLMs (Ollama): model policy, deterministic prompt scanner, route-through guarding — the complement to IGEL AI Armor. 18 MCP tools (preview)
pypi MIT -
Pluggable, observable RAG MCP server — hybrid retrieval (BM25+dense+RRF), BEIR-benchmarked rerankers (BGE / TypeSafe Jev / LLM), Streamlit dashboard + Langfuse, multimodal ingestion
-
Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.
★ 43 -
argusgithub.com/maisymylod/argusupdated this year
Natural-language earth-observation: an LLM agent calls geospatial tools (also exposed over MCP), runs an NDVI/ONNX imagery pipeline on public Sentinel-2 data, and renders to a WebGL map.
MIT -
hecatoncheiregithub.com/srose69/hecatoncheireupdated this year
Multi-agent MCP server for continuous code development with local LLM orchestration. Writer, Validator, Observer — role-separated AI agents with feedback loops.
NOASSERTION ★ 1 -
nexus-agentgithub.com/raykavin/nexus-agentupdated this year
Multi-provider LLM agent backend with RAG, Python toolpacks, SSE streaming and MCP server. Supports OpenAI, OpenRouter and Ollama with per-session routing, tool-calling loop and OpenTelemetry observability.
★ 2 -
Runtime debugging for LLM agents: launch, trace, break and observe live programs over MCP, no recompilation.
MIT -
Model Context Protocol server for backtest-kit: lets an LLM agent observe the live trading portfolio and open or close positions through guarded tools
npm MIT -
MCP server that enables LLM agents to maintain consistent personality, memory, and emotions across sessions, along with a telemetry dashboard for real-time observability.
★ 2 -
An LLM agent plays Heroes of Might and Magic III on the VCMI engine — fair, verifiable, recordable. MCP server (33 tools) + AgentBridge patch: player-visible observation, player-legal actions, real UI clicks, fog-of-war BFS exploration, evidence ledger, 1080p recording. 让 LLM 像玩家一样亲自玩《英雄无敌 III》。
NOASSERTION ★ 2 -
ebpf-mcp-tracergithub.com/blackdragoon26/ebpf-mcp-tracerupdated this year
A secure MCP server that connects LLMs and the Linux kernel by orchestrating `bpftrace` for natural-language, kernel-level observability.
★ 1 -
Chat with your documents — production-grade RAG on Spring Boot 4 + Spring AI 2.0 + pgvector, exposed as both a REST API and an MCP server for Claude Desktop, with eval-gated CI and LLM cost observability.
MIT -
neuro-mcp-unified-orchestration-enginegithub.com/bitsandbrainsai/neuro-mcp-unified-orchestration-engineupdated this year
Production-grade NeuroMCP orchestration engine that unifies n8n workflows with agentic LLM ecosystems, delivering secure, deterministic, and scalable automation. Features context-aware execution, multi-transport support, structured observability, & fault-tolerant design, powering AI-native, resilient, & high-performance enterprise infrastructure.
-
VXgithub.com/Arnaroo/VXactive
AI-agent-controllable desktop genome and transcriptome viewer. Native MCP server (43 tools) and embedded HTTP API let LLM assistants observe, drive, and analyse alongside the user. OpenGL rendering, 50+ built-in analyses, unified chromosome- and transcript-space (ribo-seq, direct RNA, long-read). Linux, Windows, macOS.
NOASSERTION ★ 6 -
Agentic multi-cloud FinOps, security auto-remediation and AI observability platform. FastAPI + LangGraph agent swarm, corrective RAG (Qdrant), PyTorch CNN anomaly detection, Groq + Gemini LLM gateway, MCP server, human-approved Terraform fixes, Docker..
MIT ★ 3 -
pulse-flight-deals-mcpgithub.com/yaotsakpo/pulse-flight-deals-mcpupdated this year
MCP server that lets an AI agent judge whether a flight price is actually a deal, grounded in observed fare history. Answers 'is $X for this route a good price?' with real numbers an LLM cannot produce on its own.
npm MIT -
Model Context Protocol (MCP) for connecting Cryostat to Large Language Models (LLMs)
NOASSERTION -
Behavioral safety, vulnerability probing, and product-risk auditing platform & MCP server for Generative AI & Large Language Models.
pypi Apache-2.0 ★ 2 -
Local-first observability dashboard for AI agents. MCP-native. Look at every span your agents emit.
pypi MIT ★ 7 -
MCP server for SolarWinds Observability platform integration
npm MIT -
observability_mcp_servergithub.com/juanmaalt/observability_mcp_serverupdated this year
MCP server for querying New Relic logs through natural language. Built with Kotlin.
-
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.
-
MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails
npm -
Build for agents — from the AI Gateway to the entire application stack.
Apache-2.0 ★ 293 -
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 -
Time-travel debugging for AI agents: record, fork and replay runs, trajectory evaluation, MCP server
-
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.
npm MIT ★ 2 -
Open-source, model-agnostic control plane for LLM agents — tamper-evident, human-gated, replayable run bundles with full trace history, model I/O, and cost telemetry. TypeScript · React · MCP · OpenAPI. MIT, published on npm.
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 -
Self-hosted observability for agentic debugging: traces, logs, replay, AI cost, Agent Action Graphs, MCP, profiles, and usage analytics in one evidence graph.
MIT ★ 2 -
observable-agentgithub.com/gajanangitte/observable-agentupdated this year
A local AI agent that turns self hosted SigNoz into a sensor: it detects an SLO breach through the SigNoz MCP server, applies a policy gated fix, verifies it, and rolls back if it does not hold. Governed autonomy, a carbon signal, and accessibility as telemetry. Agents of SigNoz hackathon, all three tracks.
MIT