What is infraops-mcp-server CLAUDE.md?

A project instruction file for an infrastructure operations server. It documents how a TypeScript server is built, tested, run, and organized across several infrastructure providers.

Use it when developing or maintaining the server, especially when building, testing, debugging, or working with its provider integrations.

It gives an agent consistent project-specific guidance when working on this server and clarifies commands, structure, and operating constraints.

How AlobarQuest/infraops-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to AlobarQuest/infraops-mcp-server. 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/AlobarQuest/infraops-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/AlobarQuest/infraops-mcp-server

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/alobarquest/infraops-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/alobarquest/infraops-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/alobarquest/infraops-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/alobarquest/infraops-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 6,361 This file is loaded in full into every session.

When invoked 6,361 The same file — it is already loaded in full.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.06361	$0.06361
Opus 5	$0.03180	$0.03180
Sonnet 5	$0.01272	$0.01272
Haiku 4.5	$0.00636	$0.00636

Measured 6d ago against content hash 55a5773f7796, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

infraops-mcp-server CLAUDE.md scanned grade B 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 6d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Dev** (`instance: "dev"`): `orb run -m $VPS_DEV_ORB_MACHINE bash -c <cmd>` against an OrbStack Linux machine. The optional `VPS_DEV_ORB_MACHINE` env var selects the OrbStack machine name and defaults to `"ubuntu"` (s

CLAUDE.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

InfraOps MCP Server

Multi-provider MCP server for infrastructure operations (v3.3.0). TypeScript, Node.js 18+, stdio transport.

Quick Reference

Build: npm run build (tsc → dist/)
Dev: npm run dev (tsx watch)
Entry: src/index.ts → dist/index.js
Tests: npx vitest run (test files in tests/)
Test watch: npm run test:watch (vitest watch mode)
Clean: npm run clean (removes dist/)
Run: use ./start.sh for full env var initialization (fetches secrets from BWS); use node dist/index.js only for standalone debugging where providers without env vars stay disabled.

Architecture

src/
├── index.ts              # Server init, conditional provider registration
├── constants.ts          # CHARACTER_LIMIT (25K), DEFAULT_LIMIT, REQUEST_TIMEOUT
├── types.ts              # Coolify API response interfaces + CoolifyPrivateKey
├── schemas/common.ts     # Shared Zod schemas (UUID, pagination, response format, CoolifyInstance)
├── services/             # API clients (one per provider)
│   ├── coolify-client.ts # Multi-instance support (prod/dev)
│   ├── github-client.ts  # GitHub REST API (deploy keys, repos)
│   ├── hetzner-client.ts
│   ├── cloudflare-client.ts
│   ├── namecheap-client.ts
│   ├── supabase-client.ts
│   ├── ssh-client.ts     # SSH backend (prod — Hetzner)
│   ├── orb-client.ts     # OrbStack `orb run` backend (dev — local)
│   └── vps-dispatch.ts   # Routes vps_* ops to ssh/orb based on instance
└── tools/                # Tool registration modules (registerXxxTools functions)
    ├── projects.ts, applications.ts, private-keys.ts,
    │   deployments.ts, env-vars.ts, databases.ts,
    │   servers.ts, services.ts, control.ts, diagnostics.ts,
    │   storages.ts, scheduled-tasks.ts, database-backups.ts,
    │   github-apps.ts, docs.ts                            # Coolify (~86 tools)
    ├── github.ts                                         # GitHub (4 tools)
    ├── hetzner-servers.ts, hetzner-networking.ts          # Hetzner (26 tools)
    ├── vps.ts                                             # VPS SSH (7 tools)
    ├── namecheap-domains.ts, namecheap-dns.ts             # Namecheap (19 tools)
    ├── cloudflare-dns.ts, cloudflare-pages.ts,
    │   cloudflare-workers.ts, cloudflare-r2.ts,
    │   cloudflare-tunnels.ts, cloudflare-security.ts      # Cloudflare (44 tools)
    └── supabase-projects.ts, supabase-database.ts,
        supabase-functions.ts, supabase-config.ts          # Supabase (28 tools)

Read the full file on GitHub · 332 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.

6d ago First seen · 332 lines · 6,361 tokens per session scan B 55a5773f7796

Subscribe to this mod's changes

infraops-mcp-server CLAUDE.md is an instructions file published in the GitHub repository AlobarQuest/infraops-mcp-server (0 stars, last pushed 2d ago), licensed MIT. It adds 6,361 tokens to every session, about $0.0318 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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 · 5,182 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

infraops-mcp-server: Instructions file for Claude Code