Smartest TVSAFE
📺 Control any smart TV with natural language. Play Netflix by name from your terminal. PyPI: stv · MCP server · LG/Samsung/Roku/Android
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
📺
smartest-tv
The CLI your TV has been waiting for.
Play Netflix / Apple TV+ / YouTube / Spotify by name. Cast URLs. Multi-room audio. AI concierge. All from your terminal.
2772250bd716OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add stv -- None stv==1.3.3
Exposed tools (23)
19 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
tv_audio | read | Multi-room audio mode — play music with screens off. |
tv_cast | read | Cast a Netflix/YouTube/Spotify URL to the TV. |
tv_display | read | Turn the TV into a display — show dashboards, messages, clocks, or any URL. |
tv_groups | read | List all TV groups and their members. |
tv_history | read | Show recent play history. |
tv_insights | read | Get viewing insights, screen time, or subscription value analysis. |
tv_launch | read | Launch an app, optionally with a deep link. |
tv_list_tvs | read | List all configured TVs with name, platform, IP, and default status. |
tv_next | read | Play the next episode. Continues from watch history. |
tv_notify | read | Show a toast notification on the TV screen. |
tv_play | read | Find content by name and play it on TV. |
tv_power | read | Turn TV on or off. |
tv_queue | destructive | Manage the play queue. Actions: add, show, play, skip, clear. |
tv_recommend | read | Get personalized recommendations based on watch history + trending. |
tv_resolve | read | Resolve a content name to its platform ID without playing. |
tv_scene | write | Run or list scene presets. Built-in: movie-night, kids, sleep, music. |
tv_screen | read | Turn screen on or off (audio continues when off). |
tv_state | read | Get unified live TV state: playback, volume, input, power. |
tv_state_watch | read | Stream tv_state snapshots via progress notifications. |
tv_status | read | Get TV status: current app, volume, mute, model, firmware. |
tv_sync | write | Play content on multiple TVs simultaneously (party mode). |
tv_volume | write | Get or set volume, step up/down, or toggle mute. All in one tool. |
tv_whats_on | read | Show trending content on Netflix and/or YouTube. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (8 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (14)
tv_queue
.clawhubignore
.coderabbit.yaml
url = "http://203.0.113.50:8911"
curl http://127.0.0.1:8910/sse # MCP SSE stream
curl http://127.0.0.1:8911/api/ping # REST API health check
"url": "http://192.168.1.50:8910/sse"
stv multi add friend --platform remote --url http://203.0.113.50:8911
mac_bytes = bytes.fromhex(self.mac.replace(":", "").replace("-", ""))mac_bytes = bytes.fromhex(mac.replace(":", "").replace("-", ""))mac_bytes = bytes.fromhex(self.mac.replace(":", "").replace("-", ""))docs/assets/demo.gif
docs/assets/hero-social.png
docs/assets/hero.png
Gates applied: no_behavioural_pass.
2772250bd716full audit observations/trust-audit/mcp-server/hybirdss__smartest-tv.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 2772250bd716 | SAFE | B | 89 | first audit |
Questions
What is the Smartest TV MCP server?
📺 Control any smart TV with natural language. Play Netflix by name from your terminal. PyPI: stv · MCP server · LG/Samsung/Roku/Android
What tools does Smartest TV expose?
23 in total: 19 read-only, 3 that write, and 1 that can delete or overwrite (tv_queue). Every one is listed on this page with its risk.
Is Smartest TV safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Smartest TV need?
It reads STV_API_KEY, STV_CACHE_API_KEY and STV_LICENSE_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Smartest TV run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as stv.
How current is this page?
The grade is for one exact copy of the source (2772250bd716), read on 2026-10-08. The repository is watched and re-audited when it changes.