What is homelab-asset-db-mcp CLAUDE.md?

A guide for AI coding agents working on a server that reads a Markdown homelab asset database. A homelab is a privately managed collection of computers and network devices at home.

Guiding maintenance of the server, including its four read-only lookup tools, database path settings, and parser changes.

It explains the project's design, data-protection rules, parser behavior, and coding conventions so changes fit the repository and avoid exposing private inventory details.

How McCavity/homelab-asset-db-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to McCavity/homelab-asset-db-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/McCavity/homelab-asset-db-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/McCavity/homelab-asset-db-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/mccavity/homelab-asset-db-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mccavity/homelab-asset-db-mcp/claude-md)

Your own site

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

Per session 638 This file is loaded in full into every session.

When invoked 638 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	$0.00638	$0.00638
Opus 5.5	$0.00255	$0.00255
Sonnet 5.5	$0.00128	$0.00128
Haiku 4.5	$0.00064	$0.00064

Measured 2mo ago against content hash 88f7fc1449e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

homelab-asset-db-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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

homelab-asset-db-mcp — Conventions for AI agents

Last update: 2026-07-17

This file orients AI coding agents (Claude Code, Codex, etc.) working on this repository. Humans should read README.md first.

What this project is

A Model Context Protocol server that exposes a Markdown-based homelab asset database as four read-only lookup tools. Sibling to iobroker-mcp, paperless-bulk-mcp and nanobanana-render-mcp — same FastMCP scaffolding, different domain. Transport: stdio. Framework: FastMCP.

Key design choices

Single server.py, no package split. Four tools, ~300 lines. Split only if it grows well past that.
Data lives in a file the user owns, not in this repo. The real asset-db.md is gitignored; only the fictional asset-db.sample.md is committed. This keeps private homelab data (IPs, MACs, hostnames) out of a public repository — never add a real inventory here.
Path resolution: ASSET_DB_PATH env wins, else the bundled sample. A non-overriding .env loader (next to server.py) is a manual-run convenience; an MCP host's env config always takes precedence.
Parse on every call, no cache. The file is small; correctness beats a stale cache. Add mtime-invalidation only if inventories get large.
Bilingual section headings. CATEGORY_MAP recognises both English and German headings so the same parser serves an English sample and a German production DB. Add new headings there, not by special-casing the parser.

Parser contract

## Heading starts a section; the first |...| row after it is the header, subsequent rows are devices.
A section whose heading is not in CATEGORY_MAP is skipped (treated as prose/documentation).
Ragged rows (cell count ≠ header count) are skipped, not fatal.
A blank line resets table state, so two tables separated by prose relearn their headers.
_normalize_value maps empty cells and dashes (—, -, –) to None; _record_summary drops None fields from tool output.

Read the full file on GitHub · 56 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 · 56 lines · 638 tokens per session scan A 88f7fc1449e4

Subscribe to this mod's changes

homelab-asset-db-mcp CLAUDE.md is an instructions file published in the GitHub repository McCavity/homelab-asset-db-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 638 tokens to every session, about $0.0026 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.

fastmcp homelab mcp model-context-protocol stdio

homelab-asset-db-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
homelab-asset-db-mcp CLAUDE.mdMcCavity/homelab-asset-db-mcp	Instructions file	0	2mo ago	MIT	A	638	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

homelab-asset-db-mcp: Instructions file for Claude Code