smalltv-mcp-tools

smalltv-mcp-tools is a skill for Claude Code from yaniv-golan/smalltv-ultra-skill. It costs 136 tokens per session (1,528 once invoked), scanned A, original, MIT.

A guide for using MCP tools to control a GeekMagic SmallTV Ultra, a small ESP8266 device with a 240×240 display.

In plain words
What is it for?
Use it to inspect the device, change its display and settings, upload JPG or GIF images, or install firmware when the required local server is connected.
Why use it?
It explains which tool to use for reading device information, changing settings, uploading files, or flashing firmware, with safety checks for risky actions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the geekmagic-smalltv-ultra plugin — 2 skills shipped together

Good fit Use it to inspect the device, change its display and settings, upload JPG or GIF images, or install firmware when the required local server is connected.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yaniv-golan/smalltv-ultra-skill/smalltv-mcp-tools
Install

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.

Any agent
npx skills add yaniv-golan/smalltv-ultra-skill --skill smalltv-mcp-tools
Clone the repo
git clone --depth 1 https://github.com/yaniv-golan/smalltv-ultra-skill

Made for: Claude Code.

Or install geekmagic-smalltv-ultra, the plugin that ships this one along with the rest of its 2 skills.

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.

agentmods badge for smalltv-mcp-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaniv-golan/smalltv-ultra-skill/smalltv-mcp-tools/github.svg)](https://agentmods.dev/skills/yaniv-golan/smalltv-ultra-skill/smalltv-mcp-tools)
Your own site
<a href="https://agentmods.dev/skills/yaniv-golan/smalltv-ultra-skill/smalltv-mcp-tools"><img src="https://agentmods.dev/badge/skills/yaniv-golan/smalltv-ultra-skill/smalltv-mcp-tools/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.

agentmods 80×15 button for smalltv-mcp-tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/yaniv-golan/smalltv-ultra-skill/smalltv-mcp-tools"><img src="https://agentmods.dev/badge/skills/yaniv-golan/smalltv-ultra-skill/smalltv-mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,528 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00136 $0.01528
Opus 5 $0.00068 $0.00764
Sonnet 5 $0.00027 $0.00306
Haiku 4.5 $0.00014 $0.00153

Measured 12d ago against content hash 1642cbfb9810, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

smalltv-mcp-tools scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

When the **SmallTV Local MCP** server is connected, prefer its tools over raw HTTP (`curl`, Python `requests`). The MCP tools handle connectivity, parameter encoding, multipart uploads, and safety blocking internally.
skills/smalltv-mcp-tools/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SmallTV MCP Tools

When the SmallTV Local MCP server is connected, prefer its tools over raw HTTP (curl, Python requests). The MCP tools handle connectivity, parameter encoding, multipart uploads, and safety blocking internally.

MCP Server Identity

  • Server name: smalltv-local-mcp
  • Required config: SMALLTV_IP — the device's LAN IP address
  • Transport: local (mcp-bash over stdio)

If the MCP tools are not available (server not connected), fall back to the raw HTTP patterns in the geekmagic-smalltv-ultra skill.

Tool Overview

Tool Purpose Safety
smalltv-get-device-info Verify connectivity and model via /v.json Read-only
smalltv-read Query status, config, file listings (GET only) Read-only
smalltv-write Change settings, display, system commands Write — some endpoints destructive
smalltv-upload-file Upload JPG/GIF from local filesystem Write (idempotent)
smalltv-upload-firmware Flash .bin firmware via /update Destructive — requires confirm=true

Tool Selection Rules

  1. Always call smalltv-get-device-info first — once per session, before any other tool. Confirms the device is reachable and is a SmallTV-Ultra (not a Pro or other model).
  2. Use smalltv-read for any status check or data retrieval: /v.json, /space.json, /city.json, /album.json, /filelist?dir=..., /wifi.json?q=1, /config.json. Write endpoints (/set, /wifisave, /delete) are blocked by this tool.
  3. Use smalltv-write to change settings or control the display. Common pattern: path: "/set?param=value". Returns "OK" on success.
  4. Use smalltv-upload-file for image/GIF uploads. Pass file_path (absolute local path) and dir ("/image/" for album, "/gif" for weather GIFs). Do not attempt file uploads through smalltv-write — its string body cannot carry binary data.
  5. Use smalltv-upload-firmware only when the user explicitly requests firmware flashing. Always set confirm: true only after explicit user approval.

Read the full file on GitHub · 130 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.

  1. 12d ago First seen · 130 lines · 136 tokens per session scan A 1642cbfb9810

Subscribe to this mod's changes

smalltv-mcp-tools is a skill published in the GitHub repository yaniv-golan/smalltv-ultra-skill (9 stars, last pushed 6mo ago), licensed MIT. It adds 136 tokens to every session and 1,528 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

telephony-and-conferencing

Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…

cbrock84/headcount · 85 tokens

endpoint-management

Manages laptops, desktops and mobile devices — enrollment, configuration, patching, software distribution, and lost or compromised devices. Use this to set up device management, standardize builds, roll out software or an OS upgrade, handle a lost device, or bring an unmanaged fleet under control.

cbrock84/headcount · 61 tokens

ops-home

OPS on-demand: This skill should be used when the user asks to "homey", "smart home", or…

Lifecycle-Innovations-Limited/claude-ops · 27 tokens

aurora

Aurora Smart Home orchestrator — routing layer for all smart home skills. Use this skill when the user asks ANY smart home question and you need to decide which skill to invoke, or when a task spans multiple skills (e.g., "build a sensor that shows on a dashboard and triggers automations"). Invoke aurora FIRST before…

tonylofgren/aurora-smart-home · 133 tokens

ESPHome

ESPHome device configuration, firmware, and IoT product development. Covers ESP32, ESP32-S3, ESP32-C3, ESP32-C6, ESP32-H2, ESP32-P4, ESP8266, RP2040, RP2350, nRF52, LibreTiny, Shelly, Sonoff, Tuya, BLE proxy, Matter firmware, Thread, Zigbee, GPIO, sensor YAML, LVGL displays, LED strips, voice assistant hardware…

tonylofgren/aurora-smart-home · 192 tokens

HA Integration Dev

Home Assistant custom integration development in Python. Covers customcomponents, DataUpdateCoordinator, configflow, OAuth2, conversation agent, HACS publishing, device registry, entity platforms, services, repair issues, diagnostics, Bluetooth integrations, and multi-coordinator patterns.

tonylofgren/aurora-smart-home · 55 tokens