Proxmox MCP 控制助手 是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.2 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
这是一个基于MCP协议的开源工具,允许AI代理直接管理Proxmox虚拟化环境,涵盖VE、备份服务器、邮件网关及数据中心管理。它将复杂的虚拟化运维转化为自然语言交互,非常适合需要通过AI自动化管理私有云的DevOps工程师和系统管理员。
Proxmox MCP 控制助手 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。
这是一个基于MCP协议的开源工具,允许AI代理直接管理Proxmox虚拟化环境,涵盖VE、备份服务器、邮件网关及数据中心管理。它将复杂的虚拟化运维转化为自然语言交互,非常适合需要通过AI自动化管理私有云的DevOps工程师和系统管理员。
Proxmox MCP 控制助手 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/john-broadway/proximo
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"proxmox-mcp-----": {
"command": "npx",
"args": ["-y", "proximo"]
}
}
}
# 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 Proxmox MCP 控制助手 执行以下任务... Claude: [自动调用 Proxmox MCP 控制助手 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": {
"proxmox_mcp_____": {
"command": "npx",
"args": ["-y", "proximo"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <a href="https://john-broadway.github.io/proximo/"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/john-broadway/proximo/main/docs/brand/proximo-titlecard-dark-63e64dd5.png"> <img alt="Proximo" src="https://raw.githubusercontent.com/john-broadway/proximo/main/docs/brand/proximo-titlecard-light-c1322c4d.png" width="880"> </picture> </a> </p>
<p align="center"> <a href="https://github.com/john-broadway/proximo/actions/workflows/ci.yml"><img src="https://github.com/john-broadway/proximo/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://github.com/john-broadway/proximo/actions/workflows/codeql.yml"><img src="https://github.com/john-broadway/proximo/actions/workflows/codeql.yml/badge.svg" alt="CodeQL"></a> <a href="https://github.com/john-broadway/proximo/releases"><img src="https://img.shields.io/github/v/release/john-broadway/proximo" alt="Release"></a> <a href="https://pypi.org/project/proximo-proxmox/"><img src="https://img.shields.io/pypi/v/proximo-proxmox" alt="PyPI"></a> <a href="./pyproject.toml"><img src="https://img.shields.io/badge/python-3.12%2B-blue" alt="Python 3.12+"></a> <a href="./LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-blue" alt="License Apache-2.0"></a> </p>
<p align="center"> <a href="https://scorecard.dev/viewer/?uri=github.com/john-broadway/proximo"><img src="https://api.scorecard.dev/projects/github.com/john-broadway/proximo/badge" alt="OpenSSF Scorecard"></a> <a href="https://www.bestpractices.dev/projects/13564"><img src="https://www.bestpractices.dev/projects/13564/badge" alt="OpenSSF Best Practices"></a> <a href="https://glama.ai/mcp/servers/john-broadway/proximo"><img src="https://glama.ai/mcp/servers/john-broadway/proximo/badges/score.svg" alt="Glama score"></a> <a href="https://lobehub.com/mcp/john-broadway-proximo"><img src="https://lobehub.com/badge/mcp/john-broadway-proximo?style=flat&v=3" alt="LobeHub — grade, tools, prompts"></a> </p>
<p align="center"> <a href="https://john-broadway.github.io/proximo/">Enter the ludus ↗</a> · <a href="#quickstart">Quickstart</a> · <a href="docs/SETUP.md">Setup</a> · <a href="#the-trust-layer-what-makes-proximo-different">Trust layer</a> · <a href="#demo">Demo</a> · <a href="#surfaces--tools-one-control-plane">Tools</a> · <a href="#install--run">Install</a> · <a href="SECURITY.md">Security</a> · <a href="#documentation">Docs</a> </p>
Named for Proximo, the lanista of Gladiator. The story is the design, joint for joint.
He armed his fighter with exactly what he needed, never more. He answered for every move in the arena. A lanista, not a jailer. The Spaniard earns his name by conduct, on the record, and the helmet comes off: truth said plainly, at cost. His last act opened the cages, holding the wooden sword of his own freedom. A tool should hope to end that well.
>"Win the crowd and you will win your freedom."
The others make you pick: a read-only toy, or full keys and pray. Proximo won't. Every dangerous move is planned: the verdict, the live target and the change, before anything runs. Every move is proven: a tamper-evident record. And undoable wherever the platform gives us a primitive: a mutation captures the record it is about to change and puts it back through the vendor's own write; a risky in-container command can take a snapshot first, and refuses to run if it can't.
Trust built into the substrate, not bolted on after. Hand an AI agent the keys; keep the receipts.
Sovereign and agent-agnostic. Your metal, your token, a ledger you own. No cloud, no phone-home, no standing server unless you opt in.
The core alone, no model in the loop: the same install ships proximo-core pve GET /nodes/pve1/status (or --plan on any address: the verdict and the published schema, touching nothing). Its import closure is httpx and nothing else (measured by a test); every published address on all four products; the same arm gate, tiers and audit ledger as the MCP door. The core has its own network doors, each the 0.44 face's perimeter with the core behind it: proximo-mcp-http (MCP over streamable HTTP), proximo-http (REST, POST /tools/{name} with an OpenAPI document) and proximo-a2a (an Agent2Agent card whose skills are the six tools).
📦0.48.1: on PyPI, GitHub, and GHCR (signed multi-arch image). New in 0.48.1 (pool tokens read their pool; what a clone needs). In PVE an ACL on a deeper path replaces what is inherited there, somint pve --write --scope /pool/<name>left both tokens unable to read the pool; the recipe now also prints the grant ofPVEAuditoron the pool to the user and the write token, audit privileges only (a token minted before needs those two lines run once). The write recipe and SETUP say what a clone of a template outside the scope needs:VM.Clone,Datastore.AllocateSpaceandSDN.Use, measured from the vendor's own refusals. Recent: 0.48.0 made a restore withoutuniquesay, in its plan and its receipt, that it keeps the backup's identity. See SECURITY.md for what each control honestly holds.
Proximo runs on your machine, on demand. No daemon, no open port.
``` uvx proximo-proxmox # zero-install run (PyPI package: proximo-proxmox; command stays proximo)
```
Wire it into your MCP client as the command proximo, with the PROXIMO_* env vars; see packaging/proximo.env.example.
Docker (GHCR): docker run -i --rm … ghcr.io/john-broadway/proximo:latest. Multi-arch, SBOM, sigstore-signed provenance (gh attestation verify oci://ghcr.io/john-broadway/proximo --owner john-broadway). Mirrored to Docker Hub (docker.io/jebroadway/proximo, identical digest); GHCR stays the signed primary.
Safe by default: API-only out of the box. The two near-root edges are opt-in and say so loudly: LXC exec (PROXIMO_ENABLE_EXEC=1, near-root on the host) and the qemu-guest-agent edge (PROXIMO_ENABLE_AGENT=1, near-root in a guest). Each is scoped by its own fail-closed allowlist. Smallest footprint by construction: the door advertises six schemas and nothing else. Measured on this release,tools/listover stdio is 5,544 bytes on the wire (about 1,400 tokens at the four-bytes-a-token heuristic; 1,568 as a stock 1.5B's chat template renders it, counted by its server), and that is the whole cost of connecting; the estate behind it is searched, not loaded. There is nothing to scope: a plane you have not configured is simply not reachable, a plane you have is reachable whole, and the gates do not shrink with the doorway. PLAN and PROVE apply to every address however small the model.
The network faces (experimental, opt-in): proximo-a2a speaks Agent2Agent. proximo-http serves plain HTTP + generated /openapi.json for no-code clients. proximo-mcp-http serves MCP itself over Streamable HTTP (the SDK's native transport) for networked MCP clients: no third-party stdio→HTTP bridge, so the perimeter stays Proximo's. LXC on your Proxmox host, one line: on the PVE node as root, bash -c "$(curl -fsSL https://raw.githubusercontent.com/john-broadway/proximo/main/packaging/lxc/ct/proximo.sh)" builds a Debian 13 container running proximo-mcp-http with Proximo from PyPI, its own service user, and a minted bearer on port 41243. Community-scripts engine (MIT) pointed at Proximo's own tree, their telemetry off; the same line inside the container updates it. Details: docs/SETUP.md, files: packaging/lxc/.
All three serve the full surface through the same spine as MCP. No second code path; trust spine and token scope inherited. Fail-closed perimeter: loopback, bearer-token required off-localhost, DNS-rebind and CSRF defended. Details: SECURITY.md.
// your MCP client config (Claude Desktop / Claude Code / Cursor / …)
{
"mcpServers": {
"proximo": {
"command": "uvx",
"args": ["proximo-proxmox"],
"timeout": 60, // startup is ~3.5s; a 3s client default drops the server silently
"env": {
"PROXIMO_API_BASE_URL": "https://your-pve:8006/api2/json",
"PROXIMO_TOKEN_PATH": "/path/to/token-file" // USER@REALM!TOKENID=SECRET, by reference, never inlined
}
}
}
}
Claude Code, one line:
claude mcp add proximo --env PROXIMO_API_BASE_URL=https://your-pve:8006/api2/json \
--env PROXIMO_TOKEN_PATH=/path/to/token-file -- uvx proximo-proxmox
Or install with one click:
<sub>Both prompt for the token file path; the secret never lands in client config. No token yet? uvx proximo-proxmox mint pve prints the least-privilege runbook.</sub>
Then preflight what your token can actually do (read-only):
uvx proximo-proxmox doctor
Start with a read-only token. Proximo is useful long before you grant it write. Full token-first walkthrough: docs/SETUP.md · more install paths: Install & run.
The record defends itself:
<p align="center"> <img src="https://raw.githubusercontent.com/john-broadway/proximo/main/docs/demo/hand-the-keys.svg" alt="Hand-the-keys demo: three agent moves land in the keyed hash-chained ledger and audit_verify answers ok=True keyed=True; an in-place edit breaks the chain at the exact line (ok=False); a truncation that fools the forward walk is caught by the pinned head" width="860"> </p>
<p align="center"><sub>Three agent moves land in the keyed ledger; one entry gets edited in place; <code>audit_verify()</code> breaks at the exact line, <b>ok=False</b>; the truncation a forward walk would miss is caught against the pinned head. Real code, real crypto, nothing staged, recorded on 0.30.0. Forge a byte yourself and watch the chain refuse: <a href="VERIFY.md">VERIFY.md</a>, section 2.</sub></p>
aiskill88点评:将企业级虚拟化能力接入MCP生态,极大地降低了私有云运维门槛,实用性极强。
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,Proxmox MCP 控制助手 在MCP工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | proximo |
| 原始描述 | 开源MCP工具:The Proxmox MCP you can hand the keys — VE + Backup Server + Mail Gateway + Data。⭐8 · Python |
| Topics | 虚拟化管理私有云自动化运维 |
| GitHub | https://github.com/john-broadway/proximo |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-07-12 · 更新时间:2026-07-12 · License:Apache-2.0 · 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