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/zenixsolutions/netbox-mcp-server/agents-mdgit clone --depth 1 https://github.com/ZenixSolutions/netbox-mcp-serverWrote 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/zenixsolutions/netbox-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/zenixsolutions/netbox-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/zenixsolutions/netbox-mcp-server/agents-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 | $0.12052 | $0.12052 |
| Opus 5 | $0.06026 | $0.06026 |
| Sonnet 5 | $0.02410 | $0.02410 |
| Haiku 4.5 | $0.01205 | $0.01205 |
Grade C, and why
netbox-mcp-server AGENTS.md scanned grade C with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
6. **Never tell the user the server restricts writes.** It does not. If they want an Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `npm ci` fails with `EACCES` | A previous `sudo npm` left root-owned files in the npm cache | **Stop and hand this to the user** — it needs root, which you must not use. Tell them to run `sudo chown -R "$(whoami)" ~/.n Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Config path: `~/.codex/config.toml` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/brew/HEAD/install.sh)" How it starts
The opening of the file, as written. The whole thing — 991 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Installation runbook for AI assistants
You are an AI assistant (ChatGPT, Codex, Claude, Cursor, Gemini, or similar) helping a person install this MCP server on their Mac. This file is your instruction set. Follow it top to bottom. Do not improvise alternative install methods.
If you are a human reading this, use README.md instead — it says the same
things in fewer words.
Every command output quoted in this file was captured by running that command against
version 0.2.0. Where a step needs a live NetBox instance and therefore could not be
run, the file says so explicitly instead of asserting an output. Do not treat a
"cannot be verified here" note as permission to guess at the result — report what you
actually see.
Handing this to an AI assistant
Paste this into ChatGPT, Claude, or any assistant that can browse and run commands:
Read https://raw.githubusercontent.com/ZenixSolutions/netbox-mcp-server/main/AGENTS.md and follow it to install the NetBox MCP server on my Mac.
The repository is public, so the assistant can fetch that URL directly — no GitHub account, no auth, no copy-pasting this file around.
If your assistant cannot browse the web but can run shell commands, have it clone the
repo first (section 4B) and read AGENTS.md from disk.
0. What you are installing
netbox-mcp-server is a Model Context Protocol (MCP) server written in TypeScript. It
exposes a NetBox instance (the network / datacenter source of
truth) to an AI assistant as callable tools.
It runs locally on the user's Mac as a subprocess of their AI client, over stdio. It is not a hosted service, there is no login page, and nothing is deployed anywhere.
Facts you may need:
| Property | Value |
|---|---|
| Version documented | 0.2.0 |
| Language / runtime | TypeScript compiled to ESM JavaScript, Node.js >= 20.11 |
| npm package | @zenixsolutions/netbox-mcp, binary name netbox-mcp |
| Normal install | npx -y @zenixsolutions/netbox-mcp — no clone, no build |
| Transport | stdio only |
| Required env vars | NETBOX_URL, NETBOX_TOKEN |
| Optional env vars | NETBOX_INSECURE — and nothing else |
| Tools registered | 5, always — see below |
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.
- 5d ago First seen · 991 lines · 12,052 tokens per session scan C 3886ed869012
netbox-mcp-server AGENTS.md is an instructions file published in the GitHub repository ZenixSolutions/netbox-mcp-server (0 stars, last pushed 3d ago), licensed MIT. It adds 12,052 tokens to every session, about $0.0603 per session on Opus 5. A static security scan graded it C with 4 findings (subtle steering, asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.