What is infrastructure-mcp CLAUDE.md?

Repository instructions for an unfinished Go infrastructure MCP server. It is intended to give AI agents safe, high-level access to infrastructure such as Linux, Docker, Kubernetes, monitoring systems, and network devices.

Use it when bootstrapping or developing the server, running Go builds and tests, or checking that changes fit its planned infrastructure architecture.

It identifies the project’s current state, authoritative documentation, intended boundaries, and standard Go commands before implementation begins.

How radumalica/infrastructure-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to radumalica/infrastructure-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/radumalica/infrastructure-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/radumalica/infrastructure-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/radumalica/infrastructure-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/radumalica/infrastructure-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/radumalica/infrastructure-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/radumalica/infrastructure-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/radumalica/infrastructure-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/radumalica/infrastructure-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 886 This file is loaded in full into every session.

When invoked 886 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.00886	$0.00886
Opus 5.5	$0.00354	$0.00354
Sonnet 5.5	$0.00177	$0.00177
Haiku 4.5	$0.00089	$0.00089

Measured 2mo ago against content hash f63b2f848ad5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

infrastructure-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 2mo 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.

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.

CLAUDE.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 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 Status

This is a greenfield project. The repository currently contains only README.md — the full technical architecture and development plan. No Go code, go.mod, or CI exists yet. Read README.md before implementing anything; it is the authoritative spec.

What This Project Is

A self-hosted Infrastructure MCP Server in Go 1.24+ using the official Model Context Protocol Go SDK. It sits between AI agents (Claude, Cursor, Hermes, etc.) and infrastructure (Linux/SSH, Docker, Kubernetes, Proxmox, Grafana, Prometheus, Cisco, MikroTik, UniFi, Home Assistant, ...), exposing safe, high-level MCP tools instead of raw shell access.

Explicit non-goals: it is not an SSH wrapper, Ansible replacement, monitoring system, or Kubernetes operator.

Commands

No build tooling exists yet. Once code is bootstrapped, standard Go commands apply:

go build ./...              # build
go test ./...               # all tests
go test ./internal/inventory -run TestName   # single test
go vet ./...                # static checks

Integration tests are planned via Testcontainers and Docker Compose (Ubuntu, Alpine, Grafana, Prometheus, Loki containers). CI is GitHub Actions.

Architecture

Three layers, wired top-down:

MCP layer (mcp/tools/, mcp/prompts/, mcp/resources/) — registers tools with the MCP SDK. Tools call adapters; they never talk to infrastructure directly.
Adapter layer (internal/linux/, internal/docker/, internal/proxmox/, internal/grafana/, internal/cisco/, etc.) — one isolated package per integration, all implementing a common interface. Authentication (SSH keys, API tokens, kubeconfig) lives inside adapters and is never exposed to AI agents.
Foundation — internal/inventory/ (YAML config, validated with go-playground/validator, env-var expansion for secrets like ${GRAFANA_TOKEN}) and internal/ssh/ (golang.org/x/crypto/ssh, connection pooling planned). Entry point is cmd/server/.

Read the full file on GitHub · 58 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.

2mo ago First seen · 58 lines · 886 tokens per session scan A f63b2f848ad5

Subscribe to this mod's changes

infrastructure-mcp CLAUDE.md is an instructions file published in the GitHub repository radumalica/infrastructure-mcp (5 stars, last pushed 22d ago), licensed MIT. It adds 886 tokens to every session, about $0.0035 per session on Opus 5.5. 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.

Building agents Containers DevOps and cloud ai-agents ai-tools infrastructure mcp mcp-protocol mcp-server

infrastructure-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
infrastructure-mcp CLAUDE.mdradumalica/infrastructure-mcp	Instructions file	5	22d ago	MIT	A	886	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

infrastructure-mcp: Instructions file for Claude Code