Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
在你的电脑上运行
Kairon
概览
作者提供的说明（英文原文）
Inspect Kairon VMs, network policy and VM-edge flows from an agent. Read-only by default.
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
- 使用情况i非常新★ –
它能帮你做什么
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
- 连接方式: 在你的电脑上运行
- 传输方式: stdio
- 分类: 其他
- 你需要填写：KAIRON_KUBE_URL, KAIRON_KUBE_TOKEN, KAIRON_UI_TOKEN, KAIRON_LLM_API_KEY
安装
选择你使用的 AI 应用，然后复制设置。
安装之前
- 基础检查：1 项中通过 1 项
- 在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
- 需要你自己填写：
KAIRON_KUBE_URL,KAIRON_KUBE_TOKEN,KAIRON_KUBE_CA,KAIRON_KUBE_INSECURE,KAIRON_UI_URL,KAIRON_UI_TOKEN,KAIRON_UI_CA,KAIRON_UI_INSECURE,KAIRON_LLM_URL,KAIRON_LLM_MODEL,KAIRON_LLM_API_KEY,KAIRON_MCP_TENANT
标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。
你需要
- Docker已安装 Docker
你用的是哪个应用？
在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"kairon": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"KAIRON_KUBE_URL",
"-e",
"KAIRON_KUBE_TOKEN",
"-e",
"KAIRON_KUBE_CA",
"-e",
"KAIRON_KUBE_INSECURE",
"-e",
"KAIRON_UI_URL",
"-e",
"KAIRON_UI_TOKEN",
"-e",
"KAIRON_UI_CA",
"-e",
"KAIRON_UI_INSECURE",
"-e",
"KAIRON_LLM_URL",
"-e",
"KAIRON_LLM_MODEL",
"-e",
"KAIRON_LLM_API_KEY",
"-e",
"KAIRON_MCP_TENANT",
"ghcr.io/zyvorai/kairon-mcp:v0.10.2"
],
"env": {
"KAIRON_KUBE_URL": "your-value",
"KAIRON_KUBE_TOKEN": "your-value",
"KAIRON_KUBE_CA": "your-value",
"KAIRON_KUBE_INSECURE": "your-value",
"KAIRON_UI_URL": "your-value",
"KAIRON_UI_TOKEN": "your-value",
"KAIRON_UI_CA": "your-value",
"KAIRON_UI_INSECURE": "your-value",
"KAIRON_LLM_URL": "your-value",
"KAIRON_LLM_MODEL": "your-value",
"KAIRON_LLM_API_KEY": "your-value",
"KAIRON_MCP_TENANT": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add kairon --env KAIRON_KUBE_URL=your-value --env KAIRON_KUBE_TOKEN=your-value --env KAIRON_KUBE_CA=your-value --env KAIRON_KUBE_INSECURE=your-value --env KAIRON_UI_URL=your-value --env KAIRON_UI_TOKEN=your-value --env KAIRON_UI_CA=your-value --env KAIRON_UI_INSECURE=your-value --env KAIRON_LLM_URL=your-value --env KAIRON_LLM_MODEL=your-value --env KAIRON_LLM_API_KEY=your-value --env KAIRON_MCP_TENANT=your-value -- docker run -i --rm -e KAIRON_KUBE_URL -e KAIRON_KUBE_TOKEN -e KAIRON_KUBE_CA -e KAIRON_KUBE_INSECURE -e KAIRON_UI_URL -e KAIRON_UI_TOKEN -e KAIRON_UI_CA -e KAIRON_UI_INSECURE -e KAIRON_LLM_URL -e KAIRON_LLM_MODEL -e KAIRON_LLM_API_KEY -e KAIRON_MCP_TENANT ghcr.io/zyvorai/kairon-mcp:v0.10.2运行前请先填写空着的值。
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json
{
"mcpServers": {
"kairon": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"KAIRON_KUBE_URL",
"-e",
"KAIRON_KUBE_TOKEN",
"-e",
"KAIRON_KUBE_CA",
"-e",
"KAIRON_KUBE_INSECURE",
"-e",
"KAIRON_UI_URL",
"-e",
"KAIRON_UI_TOKEN",
"-e",
"KAIRON_UI_CA",
"-e",
"KAIRON_UI_INSECURE",
"-e",
"KAIRON_LLM_URL",
"-e",
"KAIRON_LLM_MODEL",
"-e",
"KAIRON_LLM_API_KEY",
"-e",
"KAIRON_MCP_TENANT",
"ghcr.io/zyvorai/kairon-mcp:v0.10.2"
],
"env": {
"KAIRON_KUBE_URL": "your-value",
"KAIRON_KUBE_TOKEN": "your-value",
"KAIRON_KUBE_CA": "your-value",
"KAIRON_KUBE_INSECURE": "your-value",
"KAIRON_UI_URL": "your-value",
"KAIRON_UI_TOKEN": "your-value",
"KAIRON_UI_CA": "your-value",
"KAIRON_UI_INSECURE": "your-value",
"KAIRON_LLM_URL": "your-value",
"KAIRON_LLM_MODEL": "your-value",
"KAIRON_LLM_API_KEY": "your-value",
"KAIRON_MCP_TENANT": "your-value"
}
}
}
}浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"kairon": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"KAIRON_KUBE_URL",
"-e",
"KAIRON_KUBE_TOKEN",
"-e",
"KAIRON_KUBE_CA",
"-e",
"KAIRON_KUBE_INSECURE",
"-e",
"KAIRON_UI_URL",
"-e",
"KAIRON_UI_TOKEN",
"-e",
"KAIRON_UI_CA",
"-e",
"KAIRON_UI_INSECURE",
"-e",
"KAIRON_LLM_URL",
"-e",
"KAIRON_LLM_MODEL",
"-e",
"KAIRON_LLM_API_KEY",
"-e",
"KAIRON_MCP_TENANT",
"ghcr.io/zyvorai/kairon-mcp:v0.10.2"
],
"env": {
"KAIRON_KUBE_URL": "your-value",
"KAIRON_KUBE_TOKEN": "your-value",
"KAIRON_KUBE_CA": "your-value",
"KAIRON_KUBE_INSECURE": "your-value",
"KAIRON_UI_URL": "your-value",
"KAIRON_UI_TOKEN": "your-value",
"KAIRON_UI_CA": "your-value",
"KAIRON_UI_INSECURE": "your-value",
"KAIRON_LLM_URL": "your-value",
"KAIRON_LLM_MODEL": "your-value",
"KAIRON_LLM_API_KEY": "your-value",
"KAIRON_MCP_TENANT": "your-value"
}
}
}
}浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。
这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上，无需账户。
需要你填写的值
- Kubernetes API server URL, e.g. https://k8s.example:6443. The server only offers read tools unless --allow-write is appended to the container arguments; the image never sets it.
- Bearer token for the Kubernetes API. Bind it to a Role with only the verbs the agent needs (get/list on machines for read-only use).
KAIRON_KUBE_CAenvPath, inside the container, of the CA bundle for the Kubernetes API (mount it). Leave unset to use system roots.KAIRON_KUBE_INSECUREenvSet to "true" to skip TLS verification of the Kubernetes API. Lab use only.KAIRON_UI_URLenvBase URL of kairon-ui; needed by the machine_network tool (network flows, drops, capture sessions).- Bearer token for kairon-ui.
KAIRON_UI_CAenvPath, inside the container, of the CA certificate for a self-signed kairon-ui (mount it).KAIRON_UI_INSECUREenvSet to "true" to skip TLS verification of kairon-ui. Lab use only.KAIRON_LLM_URLenvOpenAI-compatible endpoint for the optional ask tool and the summary in diagnose.KAIRON_LLM_MODELenvModel name sent to KAIRON_LLM_URL.- API key for KAIRON_LLM_URL.
KAIRON_MCP_TENANTenvScope the claim tools, diagnose and ask to this tenant.
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。
它能做什么
它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月9日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 zyvorai 验证，该账户拥有此仓库
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- – 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表
与“其他”中的其他服务器比较i
- 星标数多于此分类中其他 18697 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 18697 个服务器的 66% 更新
- 基础检查结果等于或优于此分类中其他 18697 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。
常见问题
Kairon 安全吗？
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。
它需要哪些密钥或代码？
你需要填写：KAIRON_KUBE_URL, KAIRON_KUBE_TOKEN, KAIRON_UI_TOKEN, KAIRON_LLM_API_KEY
它在我的电脑上运行还是在云端？
它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。
它还在维护吗？
GitHub 仓库最后更新于–，最新版本（0.10.2）于22天前进入注册中心。
哪些应用可以使用它？
支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Docker。
有什么可以替代它？
同一分类中有：Spec Driven Development, Remote Desktop Commander, phylokit-mcp
替代选择
同一分类中其他作者的服务器，按星标数排序。
如何看卡片：↓ 每周下载量i★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Remote Desktop Commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
在云端运行✓ desktopcommander.app
phylokit-mcp
Phylogenetic inference via IQ-TREE 3 — never returns a topology without its support
在你的电脑上运行
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Kairon
VMs that don't pretend to be Pods.
Real virtual machines, scheduled by Kubernetes, run straight on KVM. No virt-launcher pod per VM, no libvirt in the hot path, no operator zoo. A Machine is desired state, kairon-controller places it, and kairon-node runs it on FluxVM with QEMU, Cloud Hypervisor, Firecracker or FluxVM's own hypervisor.
Zero pods per VM · Four hypervisors, one CRD · eBPF on every VM edge · No silent split-brain · AI agents built in (MCP)
Dashboard tour captured against the local sample-data stack ( how ), not a production cluster.
What's new
Experimental operations: Kairon Rehearsal tests upgrades on isolated CSI copies. Advanced operations adds health-gated configuration change plans, application recovery verification, traffic/RTT placement recommendations, and incident reproduction with fix verification. Includes runnable scenarios and failure-path tests. VM/CSI and host-isolation hardware qualification is still pending.
New since v0.6.0 (latest tag: v0.10.2; the rows down to incident bundles are new in v0.10.0):
| Agent sessions (experimental) | An AgentSession is a FluxVM agent session: a sandbox VM with a git workspace, a compiled egress/filesystem/process policy, budgets, checkpoints, live forks and an event ledger, scheduled and quota-counted like a Machine. Commands can wait for an admin's approval; chunked uploads, an interactive shell, credential grants the guest never sees, and the Mac guest's screen. kaironctl session, session_* MCP tools, both SDKs and a dashboard page. Mac nodes on FluxVM 0.4.8+. Guide → | |
| Coming from virtctl | kaironctl covers virtctl's verbs: console and VNC (with screenshots), restart/soft-reboot, exports and memory dumps, guest info, SSH keys and passwords, expose, freeze, guestfs, cdrom, create clone, objectgraph, --dry-run -o yaml, wait. CLI → | |
| Self-test: is it all working? | kaironctl selftest (or the dashboard's Self-test page) boots a tiny CirrOS VM and proves power, network, hotplug, snapshot-restore and more, with live coloured logs and a PASS / FAIL / SKIP table. deploy-remote.sh --self-test runs it right after a deploy. Guide → | |
| Deploy without building locally | deploy-remote.sh --remote-build copies a small source tarball and compiles on the host, so a laptop needs no Go, no Node and no build cache. Fastest path → | |
| HTTPS by default | The dashboard and the VNC console relay serve TLS out of the box (generated or bring-your-own certificate); plain HTTP is a named opt-out. Dashboard guide → | |
| Mac Fabric (experimental) | Several Macs as one pool: each publishes its chip, macOS, Rosetta, nested virtualization and Thunderbolt Bridge; spec.apple places vz Machines by them, and a MacNetwork gives Machines on different Macs one private network over Thunderbolt. Run against simulated Macs so far. Guide → | |
| Cross-cluster DR (experimental) | A MachineProtectionPlan replicates a group of Machines to S3 and keeps their specs and restore points on a second cluster, with RPO and RTO objectives. kaironctl dr failover brings them up there in dependency order, --planned with nothing lost; kaironctl dr test restores copies into an isolated network while production runs, also on a schedule. Machines keep their VirtualNetwork addresses and DNS names follow the active site through external-dns. Guide → | |
| vGPU profiles and GPU health (experimental) | spec.devices[].profile gives a Machine a slice of a GPU (NVIDIA vGPU or MIG-backed profile) instead of a whole one, scheduled by free instances and GPU memory, created when the Machine starts and returned when it stops; unhealthy GPUs are skipped. Guide → | |
| Accelerator profiles (experimental) | A cluster-scoped MachineAcceleratorProfile names an accelerator shape (count, vendor or vGPU profile, memory per device, one PCIe root for peer to peer, one NUMA node, an RDMA NIC next to the GPUs); Machines ask for it with spec.accelerators. The profile's status says how many more Machines fit on each node. Guide → | |
| Node maintenance and DRS (experimental) | kaironctl node maintenance enter NODE cordons a node, migrates its Machines away, and stops or hibernates the ones with nowhere to go; exit puts everything back. DRS (`-drs-mode recommend | automatic) evens out reserved CPU and memory across nodes, or moves Machines off nodes whose measured CPU, memory or IO pressure (PSI) is high, and kaironctl drs plan` previews it. Guide → |
| Per-disk I/O QoS | IOPS and bandwidth limits on a Machine's root and data disks (io.throttle), with bursts, enforced by QEMU and changed live on a running Machine. Guide → | |
| NVMe-oF storage (experimental) | Kairon's CSI driver provisions nvme-tcp and nvme-rdma volumes through the kernel NVMe target with native multipath; raw Block volumes boot Machines in place and attach as data disks with per-disk QEMU I/O. Guide → | |
| Hibernate (experimental) | spec.powerState: Hibernated saves RAM and device state to disk and frees the node; resume continues the same boot, on its own node or a compatible one with shared storage. Guide → | |
| Virtual networks (experimental) | VirtualNetwork: isolated IPv4 networks routed in eBPF with a Geneve overlay, per-network gateway, egress SNAT and floating IPs. Guide → | |
| Elastic memory (experimental) | Run more Machine memory than the node has: guaranteed minimums, a virtio-balloon reclaim loop and a KaironMemoryPressure signal the scheduler respects. Guide → | |
| Topology-aware placement (experimental) | NUMA, GPU, NIC and NVMe locality: the scheduler picks the node, exact CPUs, NUMA memory and PCI devices together. Guide → | |
| Incident bundles (experimental) | kaironctl diagnose machine --deep: one redacted tar.gz with the Machine's cluster state plus QMP, cgroup, console, dataplane and pcap from its node, and an opt-in guest memory dump. Guide → | |
| Lifecycle, diagnostics and namespaces (v0.9) | kaironctl doctor, connectivity test, logs, events, sysdump, config, history/rollback; kaironctl upgrade keeps your previous Helm values. The dashboard has a namespace selector, an all-namespaces Machines view and bulk Start/Stop. Release notes → | |
| `v1` API and new dashboard | kairon.zyvor.dev/v1 is the storage version (v1beta1/v1alpha1 served, deprecated). The dashboard is redesigned and gains Storage (Atlas), Pools & claims, Images and Backups pages; kairon-ui now listens on :18082. Guide → | |
| Native macOS node | kairon-node registers an Apple silicon Mac as a Node and runs backend: vz Machines through FluxVM. Verified on an M4; multi-Mac clusters not yet. Guide → · Mac cluster → | |
| Developer ecosystem kit | Python and TypeScript SDKs, digest-pinned recipes, disposable-VM GitHub Actions, Terraform composition. Kit → | |
| Fleet automation (experimental) | Opt-in Redfish fencing, balancing, autoscaling, backup and recovery plans, template claims, usage CSV and a Fleet dashboard. Guide → | |
| Kairon vs KubeVirt benchmark | Same node, same guest, one script driving both; method and raw JSON in docs/benchmarks. | |
| Import from VMware | kaironctl import ova streams an OVA once, reads vCPU, memory and firmware from the OVF, and FluxVM converts and repairs the disk. Guide → | |
| Warm pools and claims | MachinePool keeps booted Machines ready; a MachineClaim binds one in a single reconcile tick, with per-claim egress allowlists. Guide → | |
| VM fork | kaironctl fork and the MCP fork_machine tool fork a running Machine through FluxVM. Guide → | |
| Agent sandboxes (experimental) | spec.lifecycle pauses idle Machines and wakes them on connect, deletes them after a max lifetime; paused warm pools, per-claim usage, and Sandbox classes in both SDKs. Guide → | |
| Backups | MachineBackup and MachineBackupRestore with guest filesystem freeze, plus Atlas S3 backup jobs for Atlas volumes. Incremental S3 backups with policies and GFS retention (experimental). Guide → | |
| Live disks and NICs | Hot-attach PVC disks and hot-add or remove extra NICs on running Machines (kaironctl disk, kaironctl nic). Guide → | |
| Tenant fence | kairon.zyvor.dev/tenant-fence turns spec.tenant into an east-west deny of other tenants' guest addresses in the namespace. Guide → | |
| Preemption by Halt | An opted-in high-priority Machine that can't be placed halts an opted-in lower-priority one, and it resumes when the preemptor leaves. Guide → |
| Hotplug survives restart | A stop/start boots at the hotplugged CPU and memory; hotplug-persist writes it back into spec.
只显示了开头部分；其余内容请在仓库中阅读