proxmox-mcp: Instructions file for Claude Code

CLAUDE.md

proxmox-mcp CLAUDE.md is an instructions file for Claude Code from akmalovaa/proxmox-mcp. It costs 5,829 tokens per session, scanned A, original, MIT.

A set of project instructions for proxmox-mcp, a small MCP server that connects an AI agent to Proxmox VE, a platform for managing virtual machines and containers. It documents the project, its technologies, installation options, and structure.

In plain words
What is it for?
Use it when working on or deploying the Proxmox integration, including operations involving nodes, virtual machines, containers, storage, clusters, and snapshots.
Why use it?
It gives contributors and users a shared reference for how the server is organised, distributed, and used.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is akmalovaa/proxmox-mcp's own configuration. It tells Claude Code how to work on proxmox-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything proxmox-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to akmalovaa/proxmox-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/akmalovaa/proxmox-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/akmalovaa/proxmox-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for proxmox-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/akmalovaa/proxmox-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/akmalovaa/proxmox-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/akmalovaa/proxmox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/akmalovaa/proxmox-mcp/claude-md/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.

agentmods 80×15 button for proxmox-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/akmalovaa/proxmox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/akmalovaa/proxmox-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,829 This file is loaded in full into every session.
When invoked 5,829 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05829 $0.05829
Opus 5 $0.02915 $0.02915
Sonnet 5 $0.01166 $0.01166
Haiku 4.5 $0.00583 $0.00583

Measured 4d ago against content hash 5c3afe0aa2dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

proxmox-mcp CLAUDE.md scanned grade A 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **MCP Registry**: published as `io.github.akmalovaa/proxmox-mcp` (check with `curl "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.akmalovaa/proxmox-mcp"`). `server.json` declares both the pypi an
CLAUDE.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

proxmox-mcp is a deliberately minimal MCP server for Proxmox VE — built for personal use, no extra layers. stdio by default, Streamable HTTP behind one env var. Exposes 50 tools covering nodes, QEMU VMs, LXC containers, storage, cluster operations, snapshots, guest IP lookup, RRD metrics and server self-description.

Public listings

  • GHCR image: ghcr.io/akmalovaa/proxmox-mcp:latest (multi-arch amd64 + arm64). Preferred install path.
  • PyPI: https://pypi.org/project/proxmox-ve-mcp/ — distribution name is proxmox-ve-mcp (the proxmox-mcp slot was already taken). Run via uvx proxmox-ve-mcp. The Python module is still imported as proxmox_mcp[tool.uv.build-backend] module-name in pyproject.toml reconciles the two names.
  • Glama: https://glama.ai/mcp/servers/akmalovaa/proxmox-mcp — builds the Dockerfile from main branch on Deploy.
  • MCP Registry: published as io.github.akmalovaa/proxmox-mcp (check with curl "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.akmalovaa/proxmox-mcp"). server.json declares both the pypi and oci packages; publishing is manual — see "Release flow".

Tech Stack

  • Python 3.14 with UV package manager
  • MCP Python SDK 2.x (mcp.server.mcpserver.MCPServer) — MCP server framework
  • Proxmoxer — Proxmox REST API client
  • Pydantic Settings — configuration from environment variables

Project Structure

├── Dockerfile                          # Multi-stage: uv builds the venv (--extra sentry), runs as uid 10001, EXPOSE 8000
├── compose.yaml                        # Dev-only: builds local image with build: .
├── .dockerignore                       # Deny-all + allowlist; keeps docs/ out of the context
├── .env.example                        # Template for local dev env vars
├── glama.json                          # Glama maintainers file
├── server.json                         # MCP Registry manifest (pypi + oci packages)
├── .github/
│   ├── dependabot.yml                  # Monthly uv / actions / docker bumps
│   └── workflows/
│       ├── ci.yml                      # ruff + mypy + pytest + Docker build & stdio smoke test
│       └── docker-publish.yml          # Multi-arch GHCR publish on tag pushes 'X.Y.Z'
src/proxmox_mcp/
├── __init__.py
├── __main__.py                         # `uv run python -m proxmox_mcp`
├── server.py                           # MCPServer instance (+ instructions/icons/cache_hints), health routes, transport dispatch
├── config.py                           # Settings (PROXMOX_) + TransportConfig (PROXMOX_MCP_) + risk/allowlist/redaction readers
├── client.py                           # AppContext (lazy, lock-guarded ProxmoxAPI), process-wide singleton, lifespan
├── telemetry.py                        # setup_sentry() — optional, inert without SENTRY_DSN
└── tools/
    ├── __init__.py                     # register_all() — builds the Policy, registers all modules
    ├── _common.py                      # Policy, gate, error normalization, _ctx/_tier/_json/_redact/_compact, annotations
    ├── nodes.py                        # 10 tools: status, networks, disks, services, updates, rrd, tasks
    ├── vms.py                          # 17 tools: read + IPs/rrd + lifecycle/clone/migrate + snapshots
    ├── containers.py                   # 13 tools: read + IPs/rrd + lifecycle + snapshots
    ├── storage.py                      # 2 tools: list_storage, get_storage_content
    ├── cluster.py                      # 7 tools: status, resources, backups, ha, pools, log, next_vmid
    └── server_info.py                  # 1 tool: get_server_info (risk level, versions, tool counts)

Read the full file on GitHub · 218 lines

Changes

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.

  1. 4d ago Changed · +60 lines · +3,193 tokens per session 5c3afe0aa2dd
  2. 9d ago First seen · 158 lines · 2,636 tokens per session scan A a08e791f183f

Subscribe to this mod's changes

proxmox-mcp CLAUDE.md is an instructions file published in the GitHub repository akmalovaa/proxmox-mcp (2 stars, last pushed 7d ago), licensed MIT. It adds 5,829 tokens to every session, about $0.0291 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens