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 agentmods add instructions/ionos-cloud/ionoscloud-mcp/claude-mdgit clone --depth 1 https://github.com/ionos-cloud/ionoscloud-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/instructions/ionos-cloud/ionoscloud-mcp/claude-md)<a href="https://agentmods.dev/instructions/ionos-cloud/ionoscloud-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ionos-cloud/ionoscloud-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.05871 | $0.05871 |
| Opus 5 | $0.02936 | $0.02936 |
| Sonnet 5 | $0.01174 | $0.01174 |
| Haiku 4.5 | $0.00587 | $0.00587 |
Grade A, and why
ionoscloud-mcp CLAUDE.md scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Model Context Protocol (MCP) server that enables LLMs to interact with IONOS CLOUD infrastructure. Built with the official MCP Go SDK and the IONOS CLOUD Go SDK.
Build Commands
make build # Build the binary (outputs ./ionoscloud-mcp)
make install # Install the binary to $GOBIN so MCP clients on PATH pick it up
make test # Run unit tests
make test-e2e # Binary-over-stdio (mocked API) + read-only live API checks
make fmt # Format code with gofmt
make vet # Run go vet
make lint # Run golangci-lint (read-only)
make lintfix # Run golangci-lint with --fix
make vuln # Run govulncheck against all packages
make docker # Build local Docker image (IMAGE= to override tag)
Pass VERSION=<tag> to make build or make docker to override the version string (defaults to dev).
Architecture
main.go # Entry point: arg parsing, load-mode resolution, SDK clients init, MCP server, stdio transport
server_config.go # Version resolution (ldflags > go install > vcs), resolveLoadMode()
resources.go # MCP resources (embedded docs served to LLM clients)
tools/
├── helpers.go # Shared helpers (TextResult)
├── inputs.go # Shared input structs with json/jsonschema tags
├── ionosclient/ # User-Agent string builder
├── loader/ # Lazy loaders for compute and object storage
├── dynamic/ # 'dynamic' load mode: catalog + search/describe/call meta-tools
├── compute/ # Compute Engine tools (servers, datacenters, volumes, NICs, etc.)
├── k8s/ # Managed Kubernetes tools (clusters, node pools, nodes, versions)
├── dns/ # DNS tools (zones, records, reverse records, secondary zones, DNSSEC, quota)
├── billing/ # Billing tools (invoices, usage, utilization, traffic, EVN)
├── cert/ # Certificate Manager tools (certificates, auto-certs, providers)
├── activitylog/ # Activity Log tools (contracts, events)
└── objectstorage/ # Object Storage tools (buckets, objects, access keys, regions)
docs/
├── billing/ # One doc per tool group + focus-v1.3.md (embedded as MCP resource)
├── compute/ # One doc per resource
├── k8s/ # Managed Kubernetes docs
├── dns/ # One doc per resource
├── cert/ # Certificate Manager docs
├── activitylog/ # Activity Log docs
└── objectstorage/ # Object Storage docs
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.
- yesterday Changed · -2 lines · -20 tokens per session 3e9ca8216d80
- 5d ago First seen · 177 lines · 5,891 tokens per session scan A c350d5104dfe
ionoscloud-mcp CLAUDE.md is an instructions file published in the GitHub repository ionos-cloud/ionoscloud-mcp (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,871 tokens to every session, about $0.0294 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.