What is unifi-protect-mcp CLAUDE.md?

A set of Claude Code instructions for developing a UniFi Protect MCP server. UniFi Protect is a security-camera and device platform, and MCP exposes its API as tools for an agent.

Use it when installing, building, developing, or publishing the owine/unifi-protect-mcp project.

It records the project setup and special TypeScript, Node.js, package-manager, and publishing rules developers need to follow.

How owine/unifi-protect-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to owine/unifi-protect-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/owine/unifi-protect-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/owine/unifi-protect-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/owine/unifi-protect-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/owine/unifi-protect-mcp/claude-md)

Your own site

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

Per session 4,010 This file is loaded in full into every session.

When invoked 4,010 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	$0.04010	$0.04010
Opus 5.5	$0.01604	$0.01604
Sonnet 5.5	$0.00802	$0.00802
Haiku 4.5	$0.00401	$0.00401

Measured 4d ago against content hash 0cf8783cf90f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unifi-protect-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 4d 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 · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project overview

MCP server exposing UniFi Protect's Integration API as tool calls. Built with the MCP SDK, TypeScript, and Zod for input validation. Runs on Node.js via stdio transport. Aligned with UniFi Protect API 7.3.70; one tool module per API domain under src/tools/ (the README's tool tables list them all).

Local dev setup

Node version pinned in .nvmrc (Renovate keeps it current, so read the file rather than restating the version here). Use fnm — fnm use auto-reads .nvmrc on cd. The published library declares the broader range consumers may run in engines.node in package.json (CI tests its floor and each LTS line); the .nvmrc only pins development.
Package manager: pnpm via Corepack. corepack enable, then pnpm install.
Dev install/build use pnpm; publishing uses npm publish --provenance (hybrid — npm has the most battle-tested OIDC flow).

TypeScript 6/7 side-by-side

package.json deliberately aliases both TypeScript packages — do not "simplify" this back to a single typescript entry:

"@typescript/native": "npm:typescript@<7.x>",               // real TS 7 — owns the `tsc` bin
"typescript": "npm:@typescript/typescript6@<wrapper ver>",  // vendors a TS 6 release — owns the `tsc6` bin

The typescript entry's version will usually not match the TypeScript version tsc6 reports, and that is not a typo: @typescript/typescript6 carries its own version line, independent of the TypeScript release it vendors. Compare the two with node -e 'console.log(require("typescript/package.json").version)' (wrapper version) and ./node_modules/.bin/tsc6 --version (vendored TypeScript).

typescript-eslint cannot run on TypeScript 7: the Go port ships no JS API, so typescript-estree crashes at module load with TypeError: Cannot read properties of undefined (reading 'Cjs'). Aliasing the typescript specifier to @typescript/typescript6 keeps a real JS API in front of the linter, while @typescript/native claims the tsc bin so build/typecheck use the v7 compiler with no script changes.

Read the full file on GitHub · 155 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.

4d ago Changed · +4 tokens per session 0cf8783cf90f
12d ago Changed · -1 lines · +112 tokens per session 1e5d80a71285
18d ago Changed · +32 tokens per session e05fba1df6a6
24d ago Changed · +21 lines · +1,531 tokens per session 28e7a3561ae3
25d ago Changed · +1 lines · +14 tokens per session e29b1eb46767
1mo ago Changed · +2 lines · +28 tokens per session 09f4018ab234
2mo ago First seen · 132 lines · 2,289 tokens per session scan A 370fe0d85219

Subscribe to this mod's changes

unifi-protect-mcp CLAUDE.md is an instructions file published in the GitHub repository owine/unifi-protect-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 4,010 tokens to every session, about $0.0160 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.

Hardware and IoT

unifi-protect-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unifi-protect-mcp CLAUDE.mdowine/unifi-protect-mcp	Instructions file	1	3d ago	MIT	A	4,010	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

unifi-protect-mcp: Instructions file for Claude Code