Smartest-TV
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tv_playB | Find content by name and play it on TV. This is the primary tool. Resolves the content ID automatically, then deep-links into the app on your TV. |
| tv_castB | Cast a Netflix/YouTube/Spotify URL to the TV. Paste any streaming URL. stv parses the platform and content ID automatically. |
| tv_nextB | Play the next episode. Continues from watch history. |
| tv_whats_onC | Show trending content on Netflix and/or YouTube. |
| tv_recommendB | Get personalized recommendations based on watch history + trending. |
| tv_powerB | Turn TV on or off. |
| tv_volumeA | Get or set volume, step up/down, or toggle mute. All in one tool.
|
| tv_statusB | Get TV status: current app, volume, mute, model, firmware. |
| tv_stateA | Get unified live TV state: playback, volume, input, power. Returns a single snapshot for agent branching. Fields the target driver cannot supply are returned as None. |
| tv_state_watchA | Stream tv_state snapshots via progress notifications. Emits |
| tv_screenB | Turn screen on or off (audio continues when off). |
| tv_launchA | Launch an app, optionally with a deep link. Use tv_play instead if you have a content name (not ID). Use this when you already have the exact content ID. |
| tv_notifyB | Show a toast notification on the TV screen. |
| tv_queueC | Manage the play queue. Actions: add, show, play, skip, clear. |
| tv_historyC | Show recent play history. |
| tv_resolveA | Resolve a content name to its platform ID without playing. |
| tv_sceneB | Run or list scene presets. Built-in: movie-night, kids, sleep, music. |
| tv_list_tvsA | List all configured TVs with name, platform, IP, and default status. |
| tv_syncB | Play content on multiple TVs simultaneously (party mode). Resolves once, launches on all targets via asyncio.gather. |
| tv_groupsA | List all TV groups and their members. |
| tv_insightsB | Get viewing insights, screen time, or subscription value analysis. |
| tv_displayB | Turn the TV into a display — show dashboards, messages, clocks, or any URL. The TV becomes a smart display. HTML is generated and served locally, then opened in the TV's browser. |
| tv_audioC | Multi-room audio mode — play music with screens off. Actions: play, stop, volume. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 23 tools
Most tools target distinct tasks, and descriptions help separate close cases like tv_play vs tv_launch vs tv_cast. However, tv_status vs tv_state, tv_volume vs tv_audio's volume action, and tv_power vs tv_screen have overlapping surface area that could occasionally cause misselection.
All tools use a predictable tv_snake_case convention, such as tv_play, tv_queue, tv_volume, and tv_state_watch. The only variation is noun-only vs verb-noun names, but the prefix and separators are consistent throughout.
23 tools is heavy for a smart TV control server, landing in the 16-25 range where discoverability and selection cost rise. The feature breadth is real, but some controls could likely be consolidated.
The server covers power, volume, playback, casting, queue, history, recommendations, scenes, groups, multi-room audio, and display modes. Notable gaps remain around explicit pause/resume/stop-current-playback and input/source switching.