What is netbox_mcp CLAUDE.md?

Read-only instructions for a NetBox MCP server, which lets AI systems query network-infrastructure data such as devices, sites, circuits, VLANs, and IP ranges.

Use them when developing or maintaining this server, checking its read-only safeguards, or handling NetBox API queries and paginated results.

They explain how the project works and prevent AI systems from changing NetBox data while also clarifying how result limits and pagination behave.

How chadkunsman/netbox_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chadkunsman/netbox_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/chadkunsman/netbox_mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/chadkunsman/netbox_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/chadkunsman/netbox_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chadkunsman/netbox_mcp/claude-md)

Your own site

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

Per session 7,780 This file is loaded in full into every session.

When invoked 7,780 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	$0.07780	$0.07780
Opus 5.5	$0.03112	$0.03112
Sonnet 5.5	$0.01556	$0.01556
Haiku 4.5	$0.00778	$0.00778

Measured 2mo ago against content hash 27a6cf7f50cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

netbox_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 · 740 lines

How it starts

The opening of the file, as written. The whole thing — 740 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 read-only FastMCP server that exposes NetBox API functionality to AI systems via the Model Context Protocol (MCP). The server provides comprehensive access to devices, sites, circuits, VLANs, and IP prefixes, enabling natural language queries about network infrastructure in a NetBox instance without allowing any modifications to the NetBox data.

FastMCP servers act as bridges between AI applications (like Claude, ChatGPT) and your APIs or services, allowing AI systems to discover and use your tools intelligently.

Implementation Notes

The server strictly enforces read-only access through a custom ReadOnlyAdapter that blocks any non-GET HTTP requests to the NetBox API. This ensures that AI systems can query device information but cannot make any changes to the infrastructure data.

Limit Parameter Handling

Important Implementation Note: The limit parameter in pynetbox's .filter() method controls pagination (records per HTTP request) rather than total results returned. By design, pynetbox automatically fetches all pages until it retrieves every matching record, regardless of the limit value.

To ensure tools respect the documented limits (default 50, max 1000), the MCP server implements manual enumeration that breaks iteration after the specified number of records. This prevents excessive LLM context usage while maintaining expected behavior.

This is a known limitation of the pynetbox library, not the NetBox API itself, which does support proper limit functionality.

Available Tools

The MCP server provides eighteen main tools:

Device Tools:

get_devices: Accepts structured filter parameters to query devices with specific attributes
get_device: Retrieves detailed information about a single device by name
ask_about_devices: Accepts natural language queries and converts them to appropriate API calls

Read the full file on GitHub · 740 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 · 740 lines · 7,780 tokens per session scan A 27a6cf7f50cf

Subscribe to this mod's changes

netbox_mcp CLAUDE.md is an instructions file published in the GitHub repository chadkunsman/netbox_mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 7,780 tokens to every session, about $0.0311 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 2026-09-01.

netbox_mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
netbox_mcp CLAUDE.mdchadkunsman/netbox_mcp	Instructions file	0	5mo ago	MIT	A	7,780	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

netbox_mcp: Instructions file for Claude Code