Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Bldg-7/proxmox-mcp --skill proxmox-mcp-toolsgit clone --depth 1 https://github.com/Bldg-7/proxmox-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bldg-7/proxmox-mcp/proxmox-mcp-tools)<a href="https://agentmods.dev/skills/bldg-7/proxmox-mcp/proxmox-mcp-tools"><img src="https://agentmods.dev/badge/skills/bldg-7/proxmox-mcp/proxmox-mcp-tools/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bldg-7/proxmox-mcp/proxmox-mcp-tools"><img src="https://agentmods.dev/badge/skills/bldg-7/proxmox-mcp/proxmox-mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.02877 |
| Opus 5 | $0.00027 | $0.01438 |
| Sonnet 5 | $0.00011 | $0.00575 |
| Haiku 4.5 | $0.00005 | $0.00288 |
Grade C, and why
proxmox-mcp-tools scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
PROXMOX_SSH_KEY_PATH=~/.ssh/id_rsa # Path to SSH private key (required when SSH enabled) How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proxmox MCP Tools Reference
AI Agent Skill: Complete reference for 92 Proxmox Virtual Environment management tools via Model Context Protocol
Overview
This skill teaches AI agents how to use the @bldg-7/proxmox-mcp server, which provides 92 comprehensive tools for managing Proxmox VE infrastructure through the Model Context Protocol (MCP).
What you'll learn:
- How to connect to Proxmox VE via MCP
- 92 tools organized into 14 functional domains
- Permission model (basic vs elevated operations)
- Common workflows and patterns
- Troubleshooting API quirks
Target audience: AI agents managing Proxmox infrastructure, automating VM/LXC provisioning, monitoring cluster health, or performing operational tasks.
Quick Start
Connection Setup
Required Environment Variables:
PROXMOX_HOST=pve.example.com
PROXMOX_TOKEN_NAME=mytoken
PROXMOX_TOKEN_VALUE=abc123-def456-ghi789
Optional Configuration:
PROXMOX_USER=root@pam # Default: root@pam
PROXMOX_SSL_MODE=verify # strict|verify|insecure (default: strict)
PROXMOX_SSL_CA_CERT=/path/ca.pem # CA cert (PEM) trusted in verify mode — required for self-signed certs
PROXMOX_ALLOW_ELEVATED=true # Enable create/modify/delete (default: false)
PROXMOX_PORT=8006 # Default: 8006
PROXMOX_LOG_LEVEL=info # trace|debug|info|warn|error|fatal (default: info)
SSH Configuration (for proxmox_lxc_exec):
PROXMOX_SSH_ENABLED=true # Enable SSH-based LXC exec (default: false)
PROXMOX_SSH_HOST=pve.example.com # SSH host (falls back to PROXMOX_HOST)
PROXMOX_SSH_PORT=22 # SSH port (default: 22)
PROXMOX_SSH_USER=root # SSH username (default: root)
PROXMOX_SSH_KEY_PATH=~/.ssh/id_rsa # Path to SSH private key (required when SSH enabled)
PROXMOX_SSH_NODE=pve1 # Proxmox node name (required when SSH enabled)
PROXMOX_SSH_HOST_KEY_FINGERPRINT=sha256:... # Optional host key verification
Permission Model
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/proxmox-access-control.md 9.0 KB
- references/proxmox-acme.md 2.1 KB
- references/proxmox-ceph.md 5.1 KB
- references/proxmox-certificates.md 2.4 KB
- references/proxmox-cluster.md 19 KB
- references/proxmox-lxc.md 11 KB
- references/proxmox-mcp.md 5.1 KB
- references/proxmox-networking.md 7.2 KB
- references/proxmox-nodes.md 16 KB
- references/proxmox-notifications.md 2.0 KB
- references/proxmox-pools.md 1.4 KB
- references/proxmox-snapshots-backups.md 6.2 KB
- references/proxmox-storage.md 8.8 KB
- references/proxmox-vm-lxc-shared.md 15 KB
- references/proxmox-vm.md 13 KB
- references/proxmox-workflows.md 7.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 279 lines · 54 tokens per session scan C f914952c9ab8
proxmox-mcp-tools is a skill published in the GitHub repository Bldg-7/proxmox-mcp (6 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 2,877 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…