What is MCP-ZTE-F680 CLAUDE.md?

A local MCP server for managing port forwarding on a ZTE ZXHN F680 home router through its web interface. Port forwarding makes a device or service inside a private home network reachable from the internet.

Use it to manage NAT and port-forwarding rules on a ZTE F680 router from clients such as Claude Code, Cursor, Windsurf, Cline, or the OpenAI Agents SDK.

It lets an MCP-compatible coding agent handle router port-forwarding tasks instead of requiring the user to navigate the router’s web pages manually. It uses the router’s login process and credentials to make these changes.

How Picaresco/MCP-ZTE-F680 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Picaresco/MCP-ZTE-F680. 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/Picaresco/MCP-ZTE-F680/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Picaresco/MCP-ZTE-F680

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/picaresco/mcp-zte-f680/claude-md/github.svg)](https://agentmods.dev/instructions/picaresco/mcp-zte-f680/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/picaresco/mcp-zte-f680/claude-md"><img src="https://agentmods.dev/badge/instructions/picaresco/mcp-zte-f680/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/picaresco/mcp-zte-f680/claude-md"><img src="https://agentmods.dev/badge/instructions/picaresco/mcp-zte-f680/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,342 This file is loaded in full into every session.

When invoked 2,342 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	$0.02342	$0.02342
Opus 5	$0.01171	$0.01171
Sonnet 5	$0.00468	$0.00468
Haiku 4.5	$0.00234	$0.00234

Measured 10d ago against content hash 7ec1407b7736, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

MCP-ZTE-F680 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 10d 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 · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ultima actualizacion: 2026-04-17 (v0.3.0)

ROUTER_CASA - MCP Server ZTE F680

Descripcion

MCP server (Python/FastMCP) para gestionar NAT/port forwarding en un router ZTE ZXHN F680 via su interfaz web HTTP. Publicado en PyPI como zte-f680-mcp, instalable con un solo comando (uvx zte-f680-mcp) desde cualquier cliente MCP (Claude Desktop, Claude Code, Cursor, Windsurf, Cline, OpenAI Agents SDK, etc.).

Stack y dependencias

Python 3.10+ (runtime) / FastMCP (mcp[cli]), httpx async, python-dotenv, pydantic
Build backend: hatchling (PEP 621 via pyproject.toml)
Distribucion: PyPI + TestPyPI. Transporte MCP: stdio
Auth: SHA256(password + random) + tokens dinamicos (Frm_Logintoken, Frm_Loginchecktoken)

Estructura del proyecto

ROUTER_CASA/
├── pyproject.toml              # Metadata + deps + entry point (hatchling)
├── LICENSE                     # MIT - Alberto Diaz
├── README.md                   # Publico: install en todos los clientes MCP
├── CLAUDE.md                   # Este fichero
├── .env.example                # Plantilla de credenciales
├── .gitignore
├── src/
│   └── zte_f680_mcp/
│       ├── __init__.py         # Expone main(), __version__
│       ├── server.py           # Tools MCP + lifespan (~640 lineas tras v0.3.0)
│       ├── http_client.py      # v0.3.0: sesion HTTP, login, fetch_html
│       ├── parsers.py          # v0.3.0: regex puros (formatos A, B, C)
│       ├── pages.py            # v0.3.0: fetch_X por pagina (dict limpio)
│       └── formatters.py       # v0.3.0: format_X (dict -> texto bonito)
├── tests/
│   ├── conftest.py             # v0.3.0: fixtures HTML del router
│   ├── fixtures/               # 6 HTML reales capturados
│   ├── test_parsers.py         # 18 tests unitarios
│   ├── test_pages.py           # 6 tests con monkeypatch
│   └── test_formatters.py      # 8 tests de formato
├── scripts/
│   └── capture_fixtures.py     # Regenera fixtures desde el router real
├── docs/
│   ├── changelog.md            # Historial de actualizaciones /actualiza
│   └── superpowers/            # Specs y plans de fases (v0.3.0+)
├── assets/
│   └── banner.png              # Banner del README (1498x781)
├── dist/                       # Wheels + sdist generados (gitignored)
└── venv/                       # Solo desarrollo local (gitignored)

Nota: src/zte_f680_mcp/server.py es el mismo codigo que antes vivia suelto como zte_mcp_server.py; el historial se preservo con git rename.

Read the full file on GitHub · 152 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.

10d ago First seen · 152 lines · 2,342 tokens per session scan A 7ec1407b7736

Subscribe to this mod's changes

MCP-ZTE-F680 CLAUDE.md is an instructions file published in the GitHub repository Picaresco/MCP-ZTE-F680 (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,342 tokens to every session, about $0.0117 per session on Opus 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

MCP-ZTE-F680: Instructions file for Claude Code