Spree Commerce: open-source B2B and marketplace ecommerce
Open-source B2B and marketplace ecommerce; new stores include an MCP server for AI agents.
作者提供的说明(英文原文)
Read-only vCenter inventory for migration planning: blockers, snapshots, per-core licence exposure
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。
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。
选择你使用的 AI 应用,然后复制设置。
VSPHERE_PASSWORD, VSPHERE_USERNAME, VSPHERE_BASE_URL, VSPHERE_TLS_FINGERPRINT, VSPHERE_USER_AGENT, PRINTING_PRESS_CLIENT_PROFILE, VSPHERE_MCP_READ_ONLY, VSPHERE_NO_LOCAL_DATA, VSPHERE_MCP_HTTP_TOKEN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 …”。
链接指向作者自己的文件;我们不托管也不重新打包它。打开文件后,Claude Desktop 会进行安装。
在终端中运行这条命令
运行前请先填写空着的值。
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。
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。
VSPHERE_TLS_FINGERPRINT envVSPHERE_USER_AGENT envPRINTING_PRESS_CLIENT_PROFILE envVSPHERE_MCP_READ_ONLY envVSPHERE_NO_LOCAL_DATA env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。
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10日
注册名称已通过 GitHub 账户 servosity 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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。
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。
你需要填写:VSPHERE_PASSWORD, VSPHERE_USERNAME, VSPHERE_BASE_URL, VSPHERE_MCP_HTTP_TOKEN
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)。
GitHub 仓库最后更新于–,最新版本(0.1.0)于3天前进入注册中心。
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 MCPB。
同一分类中有:Spree Commerce: open-source B2B and marketplace ecommerce, Stripe MCP, MCP Cn Commerce
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
Open-source B2B and marketplace ecommerce; new stores include an MCP server for AI agents.
MCP server integrating with Stripe - tools for customers, products, payments, and more.
8 read-only MCP platform entries; support is operation-specific; merchant live acceptance pending
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。
Unofficial. Community-built Claude Code Skill and MCP server for the VMware
API. Not affiliated with, endorsed by, or sponsored by Broadcom Inc.
▶ Watch the 30-second demo - demo data is simulated; every command shown exists in the real CLI.
Read-only vCenter inventory for migration planning: blockers, snapshots, per-core licence exposure and Proxmox mapping, as JSON an agent can use. Works with the AI you already use - ChatGPT (Plus/Pro+), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Microsoft 365 Copilot / Copilot Studio and Google Gemini via the remote path. Free, open source, runs on your laptop. Built for MSP owners. No code required.
The six agents MSP owners actually use (self-serve, works today):
| Your AI agent | How to install the VMware skill |
|---|---|
| Claude Desktop | Run installer, then Settings > Extensions to register vsphere-mcp (no JSON editing). |
| ChatGPT (paid plans) | Run installer, host vsphere-mcp over HTTPS with VSPHERE_MCP_HTTP_TOKEN set, then register it as a Developer Mode connector if your connector settings can send the bearer token. |
| Codex CLI | Paste the install prompt below. |
| Claude Code | Paste the install prompt below. |
| Claude Cowork | Paste the install prompt below. |
| GitHub Copilot (VS Code) | Run installer, add vsphere-mcp to mcp.json under the servers key, then pick Agent mode. |
For ChatGPT, run vsphere-mcp --transport http with VSPHERE_MCP_HTTP_TOKEN set, on an HTTPS host; every request sends that token. See mcp-install.md.
Big install base, but an honest heads-up: these are the remote / enterprise path, not the local binary you just installed.
| Agent | What it takes |
|---|---|
| Microsoft 365 Copilot / Copilot Studio | Not available in this build. Copilot Studio takes a remote server only, which needs the release with token-protected HTTP mode. See mcp-install.md. |
| Google Gemini | Gemini CLI is local - same as Claude Code. The Gemini app is remote only, which needs the release with token-protected HTTP mode. See mcp-install.md. |
Skill-native agents (also covered): Hermes and OpenClaw read this skill's
SKILL.mddirectly *and* speak MCP - see their install sections below. Also works with Cursor, Windsurf, Cline, Continue.dev, and Zed via MCP. Full per-tool wire-up: [docs/which-agent.md](../../docs/which-agent.md).
Run more than one agent? Install across all 51+ supported agents in one command:
npx skills add Servosity/msp-skills@latest(requires Node.js, then run the per-skill installer for the CLI/MCP binaries). See docs/which-agent.md.
.mcpbDownload VMware MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every VMware release on the releases page.)
Prefer the Claude Code plugin? Add the marketplace once, then install - works immediately, no directory listing required:
/plugin marketplace add Servosity/msp-skills
/plugin install vsphere@msp-skills
Copy this into Claude Code, Codex CLI, or Claude Cowork:
Install the VMware Skill and MCP server from Servosity/msp-skills in this agent workspace. If this workspace uses a POSIX shell (macOS, Linux, WSL, or Bash), run
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/vsphere/install.sh). If it uses Windows PowerShell, runiwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/vsphere/install.ps1 | iex. Then authenticate per the README and runvsphere-cli --helpto explore.
The same prompt works in any agent that can run shell.
Windows (PowerShell):
iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/vsphere/install.ps1 | iex
macOS / Linux:
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/vsphere/install.sh)
The installer drops both vsphere-cli (the CLI) and vsphere-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.
Verify:
vsphere-cli --version
The installer always fetches the current release - re-run it to upgrade:
macOS / Linux:
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/vsphere/install.sh)
Windows (PowerShell):
iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/vsphere/install.ps1 | iex
Claude Desktop .mcpb users: download the latest .mcpb (top of this section) and re-select it in Settings > Extensions. Claude Code plugin users: /plugin update vsphere@msp-skills.
After the installer runs, see [mcp-install.md](./mcp-install.md) and [docs/which-agent.md](../../docs/which-agent.md) for the per-agent wire-up - one section per agent, including the GitHub Copilot servers key and the remote Microsoft 365 Copilot / Copilot Studio path. Claude Desktop's Settings > Extensions panel is the simplest path; the MCP config block (for users who prefer editing JSON) is documented in mcp-install.md.
From the Hermes CLI:
hermes skills install servosity/msp-skills/skills/vsphere --force
Inside a Hermes chat session:
/skills install servosity/msp-skills/skills/vsphere --force
Hermes speaks MCP natively, so it can also use the vsphere-mcp server directly - same install path, same env vars.
Tell your OpenClaw agent (copy this):
Install the vsphere skill from https://github.com/servosity/msp-skills/tree/main/skills/vsphere. The skill defines how its required CLI (
vsphere-cli) can be installed via theopenclaw:frontmatter block.
OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.
Set the credentials the CLI needs (a vCenter SSO user with the Read-Only role is enough; VSPHERE_TLS_FINGERPRINT only for a self-signed certificate):
VSPHERE_BASE_URL=https://<vcenter> VSPHERE_USERNAME=<user> VSPHERE_PASSWORD=<password> vsphere-cli doctor
On Windows (PowerShell):
$env:VSPHERE_BASE_URL = "https://<vcenter>"
$env:VSPHERE_USERNAME = " " $env:VSPHERE_PASSWORD = " " vsphere-cli doctor
doctor checks config, paths and API reachability, then verifies the credential by logging in and reading its own session (GET /api/session): valid, invalid (HTTP 401), or an ERROR that names VSPHERE_BASE_URL when the host is not a vCenter Server.
| Question your MSP keeps asking | Command |
|---|---|
| Which VMs are blocked from migrating, and what is blocking each one? | vsphere-cli migration blockers --severity block --agent |
| Which snapshots are older than a week, and how much delta disk does each of those VMs carry? | vsphere-cli snapshots audit --older-than 7d --agent |
| How many licensable cores does this vCenter have under the 16-core-per-CPU minimum? | vsphere-cli licence exposure --agent |
| How much vCPU, RAM and storage does the Proxmox target need? | vsphere-cli migration capacity --powered-on-only --agent |
| Which Proxmox VE settings does this VM map to? | vsphere-cli migration proxmox-map --vm vm-1021 --agent |
| Can I get an RVTools-format export without a Windows machine? | vsphere-cli rvtools export --out ./acme-rvtools |
Full command reference: guide.md. For the AI-agent operating contract (--agent, --dry-run, when to confirm before mutating), see AGENTS.md.
Most VMware integrations and MCP servers proxy each question into a live API call. That's fine for one record. It falls short when the question is "which of this client's 400 VMs can move to Proxmox this weekend, and what will Broadcom charge for the rest?"
This skill can sync VMware lists into a local SQLite mirror with full-text search. The compound commands (migration blockers, snapshots audit, licence exposure, migration proxmox-map) read vCenter live through both APIs and join VMs, hosts, hardware, snapshots and disk layouts into one answer, so the AI sees the answer, not the raw data - work a stateless API wrapper can't do. They need a reachable vCenter and refuse --data-source local.
Broadcom's per-core subscriptions multiplied VMware bills for many MSPs and their clients (ServeTheHome reported 10x or more for cloud service providers). Every client with a vCenter now asks what staying costs and what leaving takes, and answering still means RVTools on a Windows jump box and an afternoon of spreadsheet work.
vsphere-cli migration blockers --severity block --agent - every VM that cannot move yet, and why.vsphere-cli licence exposure --agent - licensable cores under the 16-core-per-CPU minimum.vsphere-cli snapshots audit --older-than 7d --agent - forgotten snapshots before they stall a cutover.vsphere-cli rvtools export --out ./acme-rvtools - the RVTools CSV layout without Windows.See pain-point.md for the longer narrative.
Yes, on Plus, Pro, Team, Business, Enterprise, and Education plans (Free tier does not yet expose Developer Mode). ChatGPT connects to remote MCP servers over HTTPS, not local stdio binaries. The VMware vSphere MCP server runs locally over stdio by default. Its HTTP mode (vsphere-mcp --transport http) serves http://127.0.0.1:7777/mcp, refuses to start until VSPHERE_MCP_HTTP_TOKEN is set, requires Authorization: Bearer on every request, and needs --tls-cert/--tls-key for any other address. Step-by-step in mcp-install.md.
Yes - all of them speak MCP. Cross-tool install commands are in the matrix above and the deep-dive in docs/which-agent.md.
No. The recommended install is to paste one sentence into Claude Code or Codex - your agent reads SKILL.md and does the install. The fallback is a one-line installer per OS (bash or PowerShell). Neither path requires writing code. You'll enter your VMware credentials once.
Your data stays on your machine. The CLI and MCP server are local binari
只显示了开头部分;其余内容请在仓库中阅读