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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
Autonomous Cloud SRE & DevSecOps Platform utilizing Model Context Protocol (MCP), Enterprise RAG & Multi-Agent Swarms.
-
🤖 AI SRE - Intelligent Site Reliability Engineering Toolbox. Lean containerized CLI toolbox for AI-powered Kubernetes cluster remediation via MCP Server API. Perfect for N8N workflow integration.
MIT ★ 1 -
openshift-mcp-sre-toolsgithub.com/nedoshi/openshift-mcp-sre-toolsupdated this year
Enterprise-grade AI-powered OpenShift SRE diagnostic tools using Model Context Protocol (MCP)
-
Production-grade MCP server for SRE operations — PagerDuty, Grafana, Kubernetes, and AWS CloudWatch tools for AI assistants
MIT ★ 1 -
AI-powered SRE orchestration platform: multi-agent incident detection, autonomous remediation via MCP tool servers, and RAG-driven runbook lookup.
-
AI SRE assistant: LangGraph ReAct agent + custom MCP server (Docker/Azure Monitor telemetry) + hybrid RAG (pgvector, BM25, RRF, cross-encoder) over runbooks & post-mortems, with guardrails and LLM evals
MIT -
sre-agentgithub.com/benmoggee/sre-agentupdated this year
SRE Agent — An AI-powered MCP server for production incident triage. Takes natural-language symptom reports, plans structured investigations using Gemini, executes parallel workers (logs, metrics, deploys, runbooks), synthesizes root-cause reports, and proposes remediation patches with human approval gates.
MIT ★ 39 -
Secure Model Context Protocol server for Rootly APIs with AI SRE capabilities, comprehensive error handling, and input validation
pypi Apache-2.0 -
mttrly-mcpgithub.com/mttrly-hq/mttrly-mcpupdated this year
Remote MCP server for mttrly — AI SRE agent for server health, diagnostics, playbooks, approvals, and audit history. OAuth 2.1 over Streamable HTTP.
MIT -
InfraGeniusgithub.com/aryasoni98/InfraGeniusupdated this year
InfraGenius is a comprehensive AI-powered platform designed specifically for DevOps, SRE, Cloud, and Platform Engineering professionals. It provides industry-level expertise through advanced AI models, optimized for infrastructure operations, reliability engineering, and cloud architecture.
MIT ★ 3 -
Open-Source AI Platform for DevOps, SRE, Cloud, and Platform Engineering
Apache-2.0 ★ 12 -
AI-assisted JVM diagnostics for SREs: Go CLI, Web UI, MCP and Kubernetes ephemeral-container capture.
Apache-2.0 ★ 2 -
MCP server for the CCX admin API (SRE / operations) via AI assistants
npm Apache-2.0 -
Cloud-native personal finance platform with evidence-backed AI agents, agentic SRE/FinOps workflows, MCP, OpenTelemetry, Kubernetes and Terraform.
★ 1 -
AI SRE agent that detects, diagnoses and safely fixes incidents in a microservices app: Kubernetes, Prometheus/Grafana, MCP tools and human-in-the-loop approvals.
MIT ★ 1 -
Model Context Protocol server for VibeInfra — lets an AI agent browse the SRE incident catalog, read live sandbox capacity and look up infrastructure terms.
npm MIT -
장애진단: 카카오·네이버 로그인, 홈택스·정부24, 은행·결제, AI API, 클라우드·SaaS, 공공데이터 API를 5분마다 외부에서 확인하는 SRE 대시보드
-
deploycheckgithub.com/SarthakDhatrak/deploycheckupdated this year
An autonomous AI Site Reliability Engineer (SRE) built as a Model Context Protocol (MCP) server. It plugs into your IDE to analyze deployments, detect drifts, and automatically diagnose crash logs by cross-referencing your Git history.
★ 1 -
AI-powered SRE incident response agent using Claude (Anthropic) + MCP – auto-diagnoses Kafka lag, CrashLoopBackOff, and TLS expiry on live EKS clusters | 12 operational tools, approval-gated mutations, full audit log
-
Dstl8 CLI, TUI, and MCP server for the telemetry-native AI SRE. One command connects Kubernetes, OpenTelemetry, and AWS, then brings root cause and the fix into Claude Code, Cursor, and Codex.
NOASSERTION ★ 7 -
prometheus-mcp-geminigithub.com/thenameisvikash/prometheus-mcp-geminiupdated this year
AI-powered Prometheus monitoring with Gemini CLI. Natural language RCA for SRE teams.
MIT -
cloud-shoplitegithub.com/dhanalakshmikm25/cloud-shopliteupdated this year
Cloud-native microservices platform on AWS EKS with an AI-Ops bot and an MCP agent for self-healing SRE automation.
-
toolbeltgithub.com/aragaobruno/toolbeltupdated this year
SRE-grade AI Agent Toolchain & Skill Harness. Optimized for context efficiency, robust rate-limiting, and deterministic tool execution.
MIT ★ 2 -
Autonomous AI SRE & operations platform for Kubernetes and homelabs. Powered by Hermes Agent, a FastMCP tool gateway, and zero-trust Telegram Human-in-the-Loop guardrails.
MIT -
AI/ML-powered diagnostic engine for SRE Observability on Konflux and OpenShift. It uses the Model Context Protocol (MCP) and 40+ tools to analyze logs, metrics, and traces, enabling automated RCA and predictive analysis.
pypi Apache-2.0 ★ 11 -
aient-mcpgithub.com/aient-ai/aient-mcpupdated this year
Aient AI — MCP server for AI SRE: ask what's broken in production, get a reviewed GitHub fix PR. Remote HTTP MCP over OAuth (+ x402 wallet transport).
MIT -
Lightweight AI butler for NAS & HomeLab via MCP. Zero port exposure, Telegram/Feishu bots, multimodal diagnostics & Docker SRE. | 基于 MCP 与大模型的轻量级私有云/NAS 智能管家。零端口暴露,支持 Telegram/飞书、多模态诊断与运维晨报。
MIT -
HomelabSentinel — an AI SRE for my homelab that asks before it acts: LangGraph agent with a human-approval gate, MCP server, BM25 RAG, evals and Langfuse tracing on a 100% local LLM.
MIT -
Read-only AI SRE for Kubernetes. Finds what's wrong, explains why with evidence, and reports to your terminal or Teams. Never changes the cluster. Bring your own model: Microsoft Foundry, OpenAI, Anthropic or Ollama.
pypi Apache-2.0 ★ 3 -
TheBlacklisted-NitroStackgithub.com/priyansh-narang2308/TheBlacklisted-NitroStackupdated this year
Protocol-0 is an MCP (Model Context Protocol) server that gives AI assistants, Claude, Cursor, ChatGPT, NitroChat, or any MCP-compatible client, real authority to act as your Site Reliability Engineer (SRE).
MIT ★ 5 -
Portfolio of Li ZhenXi (SRE, cloud and AI infrastructure), run as a production service: Go on Cloud Run with its own live SLO, an MCP server for AI agents, OpenTelemetry traces, DORA metrics and build-once keyless deploys; Next.js and Terraform
MIT ★ 1 -
Autonomous SRE agent that detects, diagnoses, and remediates Kubernetes memory issues with zero human intervention. Go watchdog + MCP server + CrewAI agents.
-
Autonomous SRE & Distributed Incident Diagnosis MCP Server using TypeScript and OpenTelemetry
MIT -
Coding agent plugins for integrating Traversal into Claude Code, Cursor, Codex, and more.
Apache-2.0 -
Capstone supervisor with RAG, data, cloud, SRE, MCP, and an approval gate.
MIT -
Autonomous Kubernetes SRE & Incident Diagnosis Engine powered by Model Context Protocol (MCP)
MIT -
RunWhen Platform MCP Server
pypi Apache-2.0 ★ 1 -
Autonomous Multi-Agent SRE & DevSecOps Incident Response Platform built with LangGraph, A2A Protocol, FastMCP, FastAPI, and Streamlit.
★ 1 -
🛡️ Autonomous SRE Incident Response & Canary Deployment Safety Room on Switch (WeMakeDevs Hackathon Track 01). Multi-agent outage triage, FastMCP telemetry, and human-in-the-loop rollback dispatch.
MIT ★ 1 -
Autonomous Level-1 SRE Incident Triage Agent built with LangGraph, FastMCP, and FastAPI. Evaluated on 30 golden incidents with 100% verified RCA and 0.0823 ECE.
★ 1 -
AI-powered Kubernetes troubleshooting via chat or MCP
Apache-2.0 ★ 9 -
Portable harness for Claude Code and Codex in DevOps/SRE work: safety rules, 23 skills, git-backed knowledge base with search, per-chat task journals, MCP server for Jira/Confluence/GitLab/Grafana/VictoriaMetrics.
MIT -
Read-only Kubernetes MCP server for AI agents: they can see everything and change nothing
npm NOASSERTION -
kafka-sentinel-mcpgithub.com/sanjay-amu/kafka-sentinel-mcpupdated this year
Read-only Kafka observability for AI agents — MCP server
pypi MIT ★ 3 -
mcp-deploy-intelgithub.com/vellankikoti/mcp-deploy-intelupdated this year
Kubernetes deployment intelligence — typed query tools + AI-synthesised risk briefs. CLI + MCP server.
pypi Apache-2.0 -
reboundgithub.com/rebound-how/reboundupdated this year
The open source toolbox for resilient operations
cargo Apache-2.0 ★ 11 -
AI on-call agent with its own MCP server, human approval before risky actions, crash recovery and full tracing.
MIT -
melisaigithub.com/dmitriimaksimovdevelop/melisaiupdated this year
Single-binary Linux performance diagnostics via eBPF/BCC, built for humans and AI agents (MCP)
Apache-2.0 ★ 66 -
MCP server wiring PagerDuty, Dynatrace, and runbook context for AI-driven incident response
Apache-2.0 -
企业级 AI DevOps MCP Server — 基于 MCP 协议的安全基础设施运维自动化(Docker / Kubernetes / SSH / 监控)
MIT -
Safe, auditable Kubernetes actions for AI agents: plan, policy-check, approve, apply.
Apache-2.0 -
Turn Markdown runbooks into agent-executable steps: read-only diagnostics run automatically, changes require human approval. Ships as an MCP server.
MIT -
Graph-native incident investigation agent on FalkorDB: multi-hop RCA, graph algorithms as MCP tools, approval-gated simulation
MIT -
Kubernetes, OpenShift, ROSA HCP, Helm and RHACS rulebook your AI calls as tools. No AI inside.
Apache-2.0 -
kopsgithub.com/kaka-milan-22/kopsupdated this year
Read-only kubectl as an MCP server for Claude Code — structured JSON, hardcoded safe verbs, one-shot triage & inventory.
MIT ★ 1 -
Turn Linux server operations into MCP tools, so AI agents can safely stand watch over your servers | 让 AI Agent 安全地运维你的 Linux 服务器
MIT -
Release Airlock — a deploy console whose WebMCP tools put agent writes through a human airlock
MIT -
SutramX MCP server (stdio + hosted HTTP): let AI agents manage monitors, incidents and status pages.
npm MIT -
Kubernetes AI ops MCP server: root-cause diagnosis across every layer, security triage, and fixes as reviewed GitOps commits. Never writes to the cluster.
Apache-2.0 ★ 1 -
Policy-controlled SSH access for AI coding agents. Typed tools, no shell; snapshot, verify and automatic rollback; a tamper-evident audit log.
AGPL-3.0