MCP server Awesome Agentic DevOps
Коммит 9 нояб. 2026 г.Предоставляет курируемый каталог MCP server и Agent Skills с системой оценки для специалистов в DevOps, Cloud, SRE и Platform Engineering.
Также известен как DevOpsAIguru123/awesome-agentic-devops
- Звёзды
- 84
- Инструменты
- —
- Загрузки, 30 дней
- —
- Последняя версия
- —
- Последний коммит
- 9 нояб. 2026 г.
- Лицензия
- MIT
Что такое Awesome Agentic DevOps MCP?
Awesome Agentic DevOps — это MCP server. Предоставляет курируемый каталог MCP server и Agent Skills с системой оценки для специалистов в DevOps, Cloud, SRE и Platform Engineering.
Сводка сгенерирована из README проекта
О Awesome Agentic DevOps MCP server
Этот репозиторий представляет собой курируемый каталог MCP server, Agent Skills и фреймворков, разработанных специально для профессионалов в области DevOps, Cloud, SRE и Platform Engineering. В отличие от простых списков для поиска, этот ресурс использует систему оценки, чтобы анализировать записи по таким критериям, как возможности выполнения действий, зрелость, операционные риски и механизмы подтверждения человеком. Приоритет отдается официальным ресурсам от таких провайдеров, как Google, Microsoft, Azure и AWS, при этом инструменты сообщества вынесены в отдельный раздел.
Пользователи могут интегрировать эти возможности в кодинг-агенты, такие как Claude Code, Cursor, Codex, VS Code или Antigravity. Одна команда позволяет установить сотни навыков непосредственно в вашу среду, с возможностью выбора официальных, сообщества или всех доступных навыков. Каталог включает специализированные инструменты для инфраструктуры как кода (IaC), реагирования на инциденты, безопасности и управления Kubernetes. Поскольку некоторые инструменты могут изменять инфраструктуру, проект уделяет особое внимание безопасности, используя выделенную модель и чек-листы для работы в режимах только для чтения (read-only) или предложений (proposal).
Что вы можете с ним делать
- 1Автоматизация рабочих процессов облачной инфраструктурыИспользуйте официальные MCP server для управления ресурсами на платформах AWS, Azure или Google Cloud.
- 2Управление инфраструктурой как кодомВыполняйте ревью Terraform plan или управляйте развертыванием Pulumi и OpenTofu с помощью специализированных MCP-источников.
- 3Реагирование на SRE-инцидентыПодключайтесь к инструментам мониторинга, таким как Grafana, Datadog или PagerDuty, для обработки алертов и операционных данных.
Взято из README проекта. Каждый вариант использования проверен на соответствие цитате из него.
Автоматические проверки
Запущено 14 нояб. 2026 г.Полный отчёт →Еще не проверено. Для сервера требуется оценка 80, отсутствие серьезных проблем и достаточно данных для нашей проверки. Как работают проверки · Что исправить, чтобы получить больше баллов
- Связанный и доступный исходный репозиторийdevopsaiguru123/awesome-agentic-devops is public and reachablegithub.com/devopsaiguru123/awesome-agentic-devops ↗Пройдено
- Пакет указывает этот репозиторий как источникНе проверялось
- Происхождение сборки (аттестация Sigstore)Не проверялось
- Open source лицензия (OSI)MITspdx.org/licenses/MIT.html ↗Пройдено
- Коммит или релиз за последний годLast commit or release 2026-11-09github.com/devopsaiguru123/awesome-agentic-devops ↗Пройдено
- OpenSSF ScorecardНе проверялось
- Имя пакета не похоже на популярный пакетНе проверялось
- Нет критических предупреждений в пакете или его зависимостяхНе проверялось
- Нет скрытых инструкций для модели0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersПройдено
- Деструктивные инструменты помеченыНе проверялось
- Удалённая конечная точка отвечает на рукопожатие MCPНе проверялось
README
Открыть на GitHubAwesome Agentic DevOps
A curated, official-first catalog of MCP servers, agent skills, AI agents, frameworks, and supporting resources for DevOps, Cloud, SRE, and Platform Engineering. It includes vendor and open-source project resources alongside a clearly labeled community-driven section.
Most agent lists stop at discovery. This one is built for operators:
- Official-first, community-inclusive — 80 entries organized into 15 catalog sections; official vendor and project resources are prioritized, while community-driven entries are separated in a dedicated community section.
- Scored, not just listed — every entry records action capability, human-approval controls, tracing evidence, maturity, and operational risk (how entries are scored).
- Audited by CI — GitHub repository entries are checked weekly for reachability, archived status, and stale push activity; non-GitHub documentation links are outside this automated check and require curator review.
- Installable, not just readable — one command installs hundreds of skills from cataloged Google, Microsoft, Azure, Azure DevOps, and Harness sources — plus a separate community set — into Claude Code, Cursor, Codex, VS Code, or Antigravity.
- Runnable, not just theoretical — documented reference-agent examples cover Terraform plan review, drift detection, and policy-driven container image releases.
Safety first: some cataloged tools and agents can change infrastructure. Prefer read-only or proposal mode, require human approval before write actions, and use least-privilege credentials — full guidance in the safety model and the practical operator safety checklist.
Contents
- Evaluation labels
- Compliance evidence checklist
- Operator safety checklist
- Top picks by use case
- Install skills into your coding agent
- Recently added
- Local reference agents
- Curated catalog
- How to contribute
Evaluation labels
| Label | Meaning |
|---|---|
| prod | assessed as production-adjacent; not a readiness guarantee |
| prototype | assessed as a useful prototype |
| mcp | MCP/server integration |
| approval | documents an approval or safety mechanism; enforcement varies |
| evidence | has tracing/evidence/evals |
| write | write-capable; review before use |
Labels are shorthand for structured fields recorded on every entry in data/repos.yaml — how entries are scored explains each field and how it is verified.
Compliance evidence checklist
Production-adjacent agent runs need a reviewable evidence packet, not just a chat transcript. Use the compliance evidence checklist to capture request context, identity and data boundaries, redacted tool calls, approval records, validation output, and follow-ups for MCP servers, skills, incident copilots, Terraform reviewers, and other DevOps agents.
At minimum, record an explicit approval before any write-capable agent mutates infrastructure, source control, CI/CD, identity, secrets, incidents, or production telemetry configuration. If the approval cannot be captured, keep the agent in read-only or proposal mode.
Operator safety checklist
Before wiring any catalog entry into cloud accounts, clusters, CI/CD, identity, secrets, databases, observability, or incident-response systems, run through the operator safety checklist. It gives teams a concrete preflight for read-only-first evaluation, domain-specific credential boundaries, no-secret-in-context handling, dry-run/proposal evidence, approval gates, blast-radius limits, and audit artifacts.
Top picks by use case
| Use case | Start with | Why |
|---|---|---|
| AWS agentic cloud automation | aws/agent-toolkit-for-aws | Official AWS-supported MCP, skills, plugins, project rules, IAM-aware controls, CloudWatch metrics, and CloudTrail auditability. |
| Azure cloud automation | microsoft/mcpmicrosoft/azure-skills | Official Microsoft MCP and skills/plugin sources for Azure resource workflows. |
| Google Cloud automation | google/mcpgoogleapis/gcloud-mcpgoogle/skills | Official Google MCP and skills sources for GCP, Cloud Run, GKE, observability, and storage workflows. |
| Source-control DevOps | github/github-mcp-serverGitLab MCP serveratlassian/atlassian-mcp-serverLinear MCP server docs | Official MCP tool surfaces for repos, issues, PRs, Jira, Bitbucket, Linear roadmap/issue workflows, and related delivery workflows. |
| Terraform and IaC | hashicorp/terraform-mcp-serverPulumi MCP Serveropentofu/opentofu-mcp-server | Official IaC MCP sources for Terraform Registry/HCP Terraform, Pulumi Cloud automation, and OpenTofu Registry documentation lookup. |
| SRE incident response | grafana/mcp-grafanadatadog-labs/mcp-serverHoneycomb MCP docsElastic Agent Builder MCP server docsPagerDuty/pagerduty-mcp-server | Official observability and incident-management MCPs for metrics, logs, traces, SLOs, triggers, indexed operational data, alerts, incidents, and on-call context. |
| FinOps and cloud cost | vantage-sh/vantage-mcp-server | Official Vantage MCP server for cloud spend analysis, budgets, anomalies, reports, and provider-resource cost context across Vantage-connected providers. |
| Security and code quality | OWASP MCP Top 10cisco-ai-defense/mcp-scannerSonarSource/sonarqube-mcp-serverokta/okta-mcp-serverSnyk Studio MCP docssnyk/studio-mcpWiz WIN MCP Server docsCrowdStrike/falcon-mcpDopplerHQ/mcp-server | Official MCPs and security resources for MCP threat modeling, MCP server scanning, code quality, application security, identity-aware workflows, secrets management, agent security, cloud-security posture, and Falcon-platform SOC automation. |
| Data platform operations | mongodb-js/mongodb-mcp-serverredis/mcp-redisgoogleapis/mcp-toolboxdbt-labs/dbt-mcpbytebase/dbhub | Official database and data-platform MCP servers for MongoDB, Redis, Google MCP Toolbox for Databases, dbt, and Bytebase-maintained DBHub. Treat DBHub as independent-vendor-backed and use read-only database credentials/approval gates for SQL execution. |
| Kubernetes and platform operations | kubernetes-sigs/mcp-lifecycle-operatorcontainers/kubernetes-mcp-serverskyhook-io/radar | Official Kubernetes SIG lifecycle tooling plus community Kubernetes/OpenShift MCP operations and cluster triage with explicit RBAC/blast-radius notes. |
| CI/CD and GitOps | jenkinsci/mcp-server-pluginargoproj-labs/mcp-for-argocdharness/mcp-server | Official Jenkins, Argo Project, and Harness resources for pipeline, build, deployment, rollback, and GitOps workflows. |
| MCP development and governance | modelcontextprotocol/python-sdkmodelcontextprotocol/typescript-sdkmodelcontextprotocol/registryDocker MCP Catalog and Toolkit | Official SDKs, registry, and Docker governance surfaces for building, packaging, and controlling DevOps MCP servers. |
| Browser automation and debugging | ChromeDevTools/chrome-devtools-mcpmicrosoft/playwright-mcp | Official browser automation MCP servers for web-app QA, performance tracing, network/console inspection, and accessibility-tree-driven browser workflows. |
| Agent frameworks and templates | google/adk-pythonGoogleCloudPlatform/agent-starter-pack | Official Google agent framework and production templates with CI/CD, evaluation, and observability. |
Install skills into your coding agent
Install hundreds of Agent Skills from the cataloged Google, Microsoft, Azure, Azure DevOps, and Harness sources with one command:
# Claude Code, macOS/Linux — installs every official skill into ~/.claude/skills/
curl -fsSL https://raw.githubusercontent.com/DevOpsAIguru123/awesome-agentic-devops/main/install/claude-code/install.sh | sh -s -- --official
Choose breadth with a flag: --official (361 skills), --community (26), or --all (387). Python 3 is the only requirement — there is no pip install step.
Pass --dry-run to preview first. Commands for Cursor, Codex, VS Code, Antigravity (Mac and Windows) — plus target folders and safety notes — are in the install guide. To install just one company or product, use the official skills catalog or the community skills catalog.
Recently added
New catalog entries appear below; notable non-entry changes (formatting, labels, tooling) are in the changelog.
| Date | Entry | Category |
|---|---|---|
| 2026-08-07 | heroku/heroku-mcp-server | Cloud / Heroku PaaS operations |
| 2026-07-25 | opentofu/opentofu-mcp-server | IaC / OpenTofu Registry MCP |
| 2026-07-23 | containers/kubernetes-mcp-server | Community / Kubernetes and OpenShift |
| 2026-07-23 | cisco-ai-defense/mcp-scanner | Security / MCP server scanning |
| 2026-07-23 | Honeycomb MCP docs | SRE / Honeycomb observability |
| 2026-07-22 | docker/hub-mcp | DevOps / Docker Hub container workflows |
| 2026-07-22 | digitalocean-labs/mcp-digitalocean | Cloud / DigitalOcean |
| 2026-07-22 | googleapis/mcp-toolbox | Data platform / database toolbox |
| 2026-07-22 | dbt-labs/dbt-mcp | Data platform / dbt |
| 2026-07-22 | bytebase/dbhub | Data platform / independent-vendor DBHub SQL MCP |
| 2026-07-22 | aquasecurity/trivy-mcp | Security / Trivy vulnerability scanning |
| 2026-07-22 | Linear MCP server docs | DevOps / Linear issue and roadmap workflows |
| 2026-07-18 | DopplerHQ/mcp-server | Security / Doppler secrets management |
| 2026-07-17 | CrowdStrike/falcon-mcp | Security / CrowdStrike Falcon SOC automation |
| 2026-07-14 | dynatrace-oss/dynatrace-mcp | SRE / Dynatrace observability |
| 2026-07-12 | harness/mcp-server | CI/CD / Harness |
| 2026-07-12 | harness/harness-skills | Agent skills / Harness |
| 2026-07-09 | redis/mcp-redis | Data platform / Redis |
| 2026-07-08 | Elastic Agent Builder MCP server docs | SRE / observability |
| 2026-07-07 | skyhook-io/radar | Kubernetes / community MCP |
| 2026-07-07 | OWASP MCP Top 10 | Agent security / MCP risk framework |
| 2026-07-06 | vantage-sh/vantage-mcp-server | FinOps / cloud cost |
| 2026-07-05 | hashicorp/vault-mcp-server | IaC / secrets management |
| 2026-07-05 | cloudflare/mcp-server-cloudflare | Cloud / edge |
| 2026-07-05 | CircleCI-Public/mcp-server-circleci | CI/CD |
| 2026-07-05 | mongodb-js/mongodb-mcp-server | Data platform |
| 2026-07-05 | backstage/backstage (mcp-actions-backend) | Platform toolkits |
Local reference agents
This repo keeps runnable reference agents under agents/.
| Path | Purpose |
|---|---|
agents/adk/terraform-plan-reviewer |
Gemini ADK agent that reviews Terraform plan output and returns structured risk findings. |
agents/adk/terraform-drift-detector |
Gemini ADK agent that reviews Terraform Cloud refresh-only plans and sends Discord-ready drift alerts. |
agents/container-image-release-advisor |
SonarCloud and Trivy container release pipeline with deterministic policy, protected approval, three reports, and an ADK/Vertex AI or Claude/Sonnet advisory stage. |
Curated catalog
The source of truth is data/repos.yaml. The catalog combines official vendor and open-source project resources with a dedicated section for community-driven tools and references. Entries include executable software as well as SDKs, documentation, security frameworks, registries, and other ecosystem resources.
Official Cloud MCP Servers and Agent Toolkits
| Repo | Labels | Operator note |
|---|---|---|
| aws/agent-toolkit-for-aws | prodmcpapprovalevidencewrite | Official AWS-supported toolkit with managed MCP server access, current AWS docs/API knowledge tools, on-demand agent skills, Claude Code/Codex plugins, and project rules for Kiro, Claude Code, Cursor, Codex, and other MCP-compatible agents. |
| awslabs/mcp | prodmcpapprovalwrite | Official AWS Labs MCP server collection; useful legacy/source reference while AWS transitions capabilities into Agent Toolkit. |
| microsoft/mcp | prodmcpapprovalwrite | Official Microsoft MCP catalog, including Azure cloud and infrastructure MCP references. |
| google/mcp | prodmcpapprovalwrite | Official Google MCP repository listing managed and open-source MCP servers for Google and Google Cloud. |
| googleapis/gcloud-mcp | prodmcpapprovalwrite | Official Google API repository for gcloud, observability, storage, and backup/disaster-recovery MCP servers. |
| GoogleCloudPlatform/cloud-run-mcp | prodmcpapprovalwrite | Official Google Cloud Platform MCP server for deploying apps to Cloud Run. |
| cloudflare/mcp-server-cloudflare | prodmcpapprovalwrite | Official Cloudflare MCP servers for account, Workers, and edge configuration workflows. |
| heroku/heroku-mcp-server | prototypemcpapprovalwrite | Official Heroku Platform MCP Server using the Heroku CLI for app lifecycle management, deploys, dyno scaling/restarts, logs, add-ons, pipelines, teams/spaces, and Heroku Postgres operations. |
| vercel/vercel-mcp-overview | prodmcpapprovalwrite | Official public overview of Vercel's hosted MCP server for project and deployment context. |
| digitalocean-labs/mcp-digitalocean | prototypemcpapprovalwrite | DigitalOcean Labs MCP integration for self-hosted cloud operations over DigitalOcean droplets, App Platform, databases, and account resources. |
Official DevOps MCP Servers
| Repo | Labels | Operator note |
|---|---|---|
| microsoft/azure-devops-mcp | prodmcpapprovalwrite | Official Azure DevOps MCP server with remote-first onboarding and local server option. |
| github/github-mcp-server | prodmcpapprovalwrite | Official GitHub MCP server for repository, issue, pull request, code, and workflow automation. |
| GitLab MCP server | prodmcpapprovalwrite | Official GitLab MCP server is documented as a GitLab-hosted endpoint rather than a standalone GitHub repo. |
| atlassian/atlassian-mcp-server | prodmcpapprovalwrite | Official Atlassian Rovo MCP server for Jira, Confluence, Jira Service Management, Bitbucket, and Compass. |
| Linear MCP server docs | prodmcpapprovalwrite | Official Linear documentation for its centrally hosted remote MCP server with OAuth 2.1 dynamic client registration, API-key support, a read-only endpoint, and tools for issue, project, roadmap, and comment workflows. |
| docker/mcp-registry | prodmcpapprovalevidence | Official Docker MCP registry and catalog source for verified containerized MCP servers. |
| docker/hub-mcp | prototypemcpapprovalwrite | Official Docker Hub MCP server for AI-assisted image discovery, image recommendations, and Docker Hub repository workflows. |
| kubernetes-sigs/mcp-lifecycle-operator | prototypemcpapprovalwrite | Official Kubernetes SIG operator for declaratively deploying and rolling out MCP servers, not a general kubectl MCP server. |
Official Security and Code-Quality MCP Servers
| Repo | Labels | Operator note |
|---|---|---|
| SonarSource/sonarqube-mcp-server | prodmcpapproval | Official SonarQube MCP server for code quality and security insights in AI agents. |
| okta/okta-mcp-server | prodmcpapprovalwrite | Official Okta self-hosted MCP server for connecting agents to Okta identity workflows. |
| OWASP MCP Top 10 | prodmcpapprovalevidence | Official OWASP MCP Top 10 documentation for assessing Model Context Protocol security risks across agentic DevOps integrations. |
| Snyk Studio MCP docs | prodmcpapprovalevidence | Official Snyk documentation for Snyk Studio agentic security workflows and Snyk MCP Server usage. |
| snyk/studio-mcp | prodmcpapprovalevidence | Official Snyk MCP server (Go) providing snyk_sca_scan, snyk_code_scan, snyk_iac_scan, snyk_container_scan, snyk_sbom_scan, snyk_secret_scan, and snyk_aibom tools via the snyk mcp CLI command. |
| snyk/agent-scan | prodapprovalevidence | Official Snyk security scanner for AI agents, MCP servers, and agent skills. |
| Wiz WIN MCP Server docs | prodmcpapprovalevidence | Official Wiz documentation for the WIN MCP server, adding CNAPP and cloud-security coverage. |
| CrowdStrike/falcon-mcp | prototypemcpapprovalwrite | Official CrowdStrike MCP server (Python, public preview) for threat detection, incident investigation, threat intelligence, endpoint inventory, identity protection, NG-SIEM, and cloud security (CSPM/CSVM). Use least-privilege API scopes; write-capable modules can change endpoint policy and detection rules. |
| DopplerHQ/mcp-server | prototypemcpapprovalwrite | Official Doppler MCP server (TypeScript, Apache-2.0) providing AI assistants access to the Doppler secrets API. Experimental; use service tokens scoped per config. Write-capable — can create/delete secrets. |
| cisco-ai-defense/mcp-scanner | prodmcpapprovalevidence | Cisco AI Defense MCP Scanner for scanning MCP servers and tools with YARA rules, LLM-as-judge, Cisco AI Defense Inspect API, dependency checks, readiness checks, and optional VirusTotal analysis. |
| aquasecurity/trivy-mcp | prototypemcpapprovalevidence | Official Aqua Security Trivy MCP plugin exposing vulnerability, misconfiguration, secret, filesystem, container image, and repository scanning to MCP clients. |
Вопросы о Awesome Agentic DevOps MCP
Какие ресурсы включены в этот каталог?
Каталог включает в себя в первую очередь официальные MCP server, Agent Skills, AI-агентов, фреймворки и вспомогательные ресурсы для DevOps, Cloud, SRE и Platform Engineering.
Как оцениваются записи в каталоге?
Записи оцениваются на основе возможностей выполнения действий, наличия механизмов подтверждения человеком, наличия данных трассировки, зрелости и операционных рисков.
Могу ли я установить эти навыки в своего кодинг-агента?
Да, вы можете установить сотни навыков от таких поставщиков, как Google, Microsoft и Azure, в таких агентов, как Claude Code, Cursor и VS Code, с помощью одной команды.