经 AI Skill Hub 精选评估,rootcause 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.1 分,适合有一定技术背景的用户使用。
rootcause 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
rootcause 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/yindia/rootcause
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"rootcause": {
"command": "npx",
"args": ["-y", "rootcause"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 rootcause 执行以下任务... Claude: [自动调用 rootcause MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"rootcause": {
"command": "npx",
"args": ["-y", "rootcause"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
AI-native SRE for Kubernetes incidents.
RootCause is a local-first MCP server that turns natural-language requests into evidence-backed incident analysis, Kubernetes diagnostics, and safer operations.
Built in Go as a single binary, RootCause is optimized for low-friction local workflows using your existing kubeconfig identity.
---
🚀 Quick Start | 🌐 Client Setup | 🛠️ Tools | 🧩 Skills | 🔒 Safety | ⚙️ Config | 🏗️ Architecture | 🤝 Contributing
---
RootCause is organized around shared Kubernetes plumbing and toolsets that reuse it.
internal/kube and injected into all toolsets.internal/policy (namespace vs cluster enforcement and tool allowlists) and internal/redact (token/secret redaction).internal/evidence gathers events, owner chains, endpoints, and pod status summaries used by all toolsets.internal/render enforces a consistent analysis output format (root causes, evidence, next checks, resources examined) and provides the shared describe helper.toolsets/ and register namespaced tools (k8s.*, linkerd.*, karpenter.*, istio.*, helm.*, aws.iam.*, aws.vpc.*) through a shared MCP registry.The MCP server runs over stdio using the MCP Go SDK and is designed for local kubeconfig usage. Optional in-cluster deployment is intentionally out of scope for Phase 1.
| Area | RootCause Capability |
|---|---|
| Incident analysis | rootcause.incident_bundle, rootcause.rca_generate, rootcause.change_timeline, rootcause.postmortem_export, rootcause.capabilities |
| Kubernetes resilience | k8s.restart_safety_check, k8s.best_practice, k8s.safe_mutation_preflight |
| Ecosystem diagnostics | ArgoCD/Flux/cert-manager/Kyverno/Gatekeeper/Cilium via *_detect and diagnose_* tools |
| Deployment safety | Automatic preflight before k8s mutating operations |
| Helm operations | Chart search/list/get, release diff, rollback advisor, template apply/uninstall flows |
| Terraform analysis | Module/provider search + terraform.debug_plan for impact/risk analysis |
| Service mesh & scaling | Linkerd/Istio/Karpenter diagnostics with shared evidence model |
| Category | Representative capabilities |
|---|---|
Kubernetes core (k8s.*) | CRUD, logs/events, graph-based debug flows, restart safety, best-practice scoring, mutation preflight |
| Ecosystem diagnostics | ArgoCD, Flux, cert-manager, Kyverno, Gatekeeper, Cilium via *_detect and diagnose_* |
Incident intelligence (rootcause.*) | Incident bundle orchestration, timeline export, RCA generation, remediation playbook, postmortem export |
Helm operations (helm.*) | Chart registry search/list/get, release status/diff, rollback advisor, install/upgrade/uninstall, template apply/uninstall |
Terraform analysis (terraform.*) | Modules/providers/resources/data source discovery + plan debugging |
Service mesh (istio.*, linkerd.*) | Proxy/config/status diagnostics, policy/routing visibility, mesh resource health |
Cluster autoscaling (karpenter.*) | Provisioning, nodepool/nodeclass, interruption and scheduling diagnostics |
Cloud context (aws.*) | IAM, VPC, EC2, EKS, ECR, STS, KMS diagnostics for cross-layer incident analysis |
| Safety and controls | Read-only mode, destructive gating, explicit confirmation, auto preflight checks before mutating K8s operations |
```bash
cp -r skills/claude/k8s-helm ~/.claude/skills/ ```
Homebrew:
brew install yindia/homebrew-yindia/rootcause
Curl install:
curl -fsSL https://raw.githubusercontent.com/yindia/rootcause/refs/heads/main/install.sh | sh
Go install:
go install .
Or build a local binary:
go build -o rootcause .
Supported OS: macOS, Linux, and Windows.
Windows build example:
go build -o rootcause.exe .
```bash
docker build -t rootcause:local .
All MCP clients use the same core values: - command: rootcause - args: usually --config /path/to/config.toml - env: optional KUBECONFIG
k8s.argocd_detect".rootcause path, --toolsets, and KUBECONFIG.npm install -g agent-browser agent-browser install
rootcause sync-skills --agent copilot --project-dir .
1) Run the server:
go run . --config config.example.toml
2) Use your existing kubeconfig (default) or point to one:
KUBECONFIG if set, otherwise ~/.kube/config.--kubeconfig and --context.3) Connect your MCP client using stdio.
RootCause is built for local development. No API keys are required in this version.
Safe-by-default workflow: diagnose read-only first, then run mutation preflight before any write operation.
---
Initialize a home config with every built-in toolset enabled and custom skills configured:
rootcause init-config
This writes ${HOME}/.rootcause/config.toml on macOS/Linux and %USERPROFILE%\.rootcause\config.toml on Windows, creates the sibling skills/ directory, and refuses to overwrite unless --overwrite is passed.
Run with a config file:
rootcause --config config.toml
Enable a subset of toolchains:
rootcause --toolsets k8s,istio
Enable read-only mode:
rootcause --read-only
Sync skills into agent-specific project directories:
rootcause sync-skills --agent claude --project-dir .
---
rootcause --config config.toml
Point your MCP client to run the command above and use stdio transport.
---
We welcome code, docs, tests, and operational feedback.
Automate web-based Kubernetes operations with agent-browser integration.
Quick setup:
```bash
browser_open, browser_screenshot, browser_click, browser_fill, browser_test_ingress, browser_screenshot_grafana, browser_health_checkbrowser_snapshot, browser_get_text, browser_get_html, browser_evaluate, browser_pdf, browser_wait_for, browser_wait_for_urlbrowser_press, browser_select, browser_check, browser_uncheck, browser_hover, browser_type, browser_upload, browser_dragbrowser_new_tab, browser_switch_tab, browser_close_tab, browser_closerootcause --config config.example.toml --toolsets k8s,linkerd,istio,karpenter,helm,aws
Create a cross-platform home config first if you do not already have one:
rootcause init-config
The generated config enables k8s, linkerd, karpenter, istio, helm, aws, terraform, and rootcause, sets stdio transport defaults, and configures ~/.rootcause/skills as the custom skill folder.
If --kubeconfig is not set, RootCause follows standard Kubernetes loading rules: it uses KUBECONFIG when present, otherwise defaults to ~/.kube/config.
Authentication and authorization use your kubeconfig identity only in this version.
---
KUBECONFIG or ~/.kube/config--kubeconfig /path/to/configSend SIGHUP to reload config and rebuild the tool registry. On Windows, SIGHUP is not supported; restart the process to reload config.
---
CONTRIBUTING.mdPLUGINS.mdconfig.tomleval/README.mdgo test ./...
README.md, prompts/prompt.md) if behavior changedFile: VS Code settings.json (MCP-enabled builds)
{
"mcp.servers": {
"rootcause": {
"command": "rootcause",
"args": ["--config", "/Users/you/.config/rootcause/config.toml"],
"env": { "KUBECONFIG": "/Users/you/.kube/config" }
}
}
}
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:rootcause 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | rootcause |
| 原始描述 | 开源MCP工具:RootCause is a local-first MCP server that turns natural-language requests into 。⭐40 · Go |
| Topics | mcpaws-mcpcontainershelmistiok8sgo |
| GitHub | https://github.com/yindia/rootcause |
| License | MIT |
| 语言 | Go |
收录时间:2026-05-22 · 更新时间:2026-05-22 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端