# TeleQ TV (npm · teleq-mcp)

Show text, slides, images, video and live HTML pages on your TV through the TeleQ app.

- Trust score: 76/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `relay.teleq.online`: 38/100, [markdown](https://verifymcp.io/servers/max4et-teleq/relay.md), [page](https://verifymcp.io/servers/max4et-teleq/relay)
- npm · `teleq-mcp`: 76/100 (this document), [markdown](https://verifymcp.io/servers/max4et-teleq/teleq-mcp.md), [page](https://verifymcp.io/servers/max4et-teleq/teleq-mcp)

## Channel facts

- Registry: `npm`
- Package: `teleq-mcp`
- Version: `1.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2259 tokens (~141/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the TeleQ TV MCP server?

TeleQ TV runs locally as an npm package, launched with npx -y teleq-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add max4et-teleq -- npx -y teleq-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "max4et-teleq": {
      "command": "npx",
      "args": [
        "-y",
        "teleq-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "max4et-teleq": {
      "command": "npx",
      "args": [
        "-y",
        "teleq-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add max4et-teleq -- npx -y teleq-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "max4et-teleq": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "teleq-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add max4et-teleq --command npx --arg -y --arg teleq-mcp
```

### Hermes

```yaml
mcp_servers:
  max4et-teleq:
    command: "npx"
    args: ["-y", "teleq-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "max4et-teleq": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "teleq-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add max4et-teleq -t stdio -c npx -a -y teleq-mcp
```

### Other

```json
{
  "mcpServers": {
    "max4et-teleq": {
      "command": "npx",
      "args": [
        "-y",
        "teleq-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 72, 0)

- [functional regression] Schema quality: 123 → 141
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 1.1.1 → 1.2.0

### 2026-11-13 (score 72)

First indexed and scored.

## MCP tools (16)

### `tv_status` (~93 tokens)

TV status

Check what the TV is showing right now (and its id, slide or queue position), whether a phone is also connected, the screen size and safe area, which tools this TV supports (capabilities), the language and country of the TV (search for content in that language) and which video services have their app on it (services_installed). Call this before changing the screen if you are unsure what is on it.

### `show_text` (~145 tokens)

Show text on the TV

Show a large, readable text card on the TV: a recipe, a list, a summary, an answer. Keep it short; people read it from the couch. Markdown subset: # headings, **bold**, - bullet lists, 1. numbered lists, blank lines between paragraphs. Returns an id for update_text.

Input parameters:

- `duration_s` (integer): Optional: clear the screen after this many seconds (1-3600). Without it the content stays until replaced or stopped.
- `markdown` (string, required): The text to show (Markdown subset). Up to 20000 characters.
- `title` (string): Optional heading shown above the text (up to 120 characters).

### `show_slides` (~155 tokens)

Present slides on the TV

Show a presentation: a list of slides, each either Markdown (rendered as a big, centred TV slide) or a complete self-contained HTML page (sandboxed, no network). The viewer moves with ←/→ on the remote; you move with slides_control. Put what you would say in notes (not shown on the TV; returned by slides_control). Up to 50 slides and 1024 KB in total. Returns an id.

Input parameters:

- `slides` (array, required): The slides in order. Each needs markdown or html (not both).
- `start_slide` (integer): Optional slide to open first (1-based). Default 1.
- `title` (string): Optional presentation title (up to 120 characters).

### `slides_control` (~94 tokens)

Move through the slides

Go to the next, previous, first, last or a given slide of the presentation on screen. Returns the slide number, the count and that slide's notes.

Input parameters:

- `action` (string, required): Where to go.
- `id` (string): Optional: the id from show_slides, to make sure the right presentation is still on screen.
- `slide` (integer): Slide number (1-based). Required for "goto".

### `show_html` (~203 tokens)

Show an HTML page on the TV

Show a self-contained HTML page (a dashboard, a chart, a scoreboard, a timer, a visual) full screen on the TV. It runs in a locked-down sandbox: scripts and CSS work, but there is no network access, so inline everything; images may be data: URIs or https:// URLs. Design for 1920x1080, large type, dark background, no scrolling, no input. To change values later without reloading, listen for window "message" events whose data is {type:"teleq:update", data} and call update_html. Returns an id.

Input parameters:

- `duration_s` (integer): Optional: clear the screen after this many seconds (1-3600). Without it the content stays until replaced or stopped.
- `html` (string, required): A complete HTML document. Up to 262144 characters.
- `title` (string): Optional title (not drawn; used in the status) (up to 120 characters).

### `update_text` (~92 tokens)

Update the text on the TV

Replace the text of a card shown with show_text, in place and without flicker. Only works while that card is still on screen.

Input parameters:

- `id` (string, required): The id returned by the show_* call that put the content up.
- `markdown` (string, required): The new text (Markdown subset). Up to 20000 characters.
- `title` (string): Optional new heading (up to 120 characters).

### `update_html` (~133 tokens)

Update the page on the TV

Update a page shown with show_html. With data, the page stays and receives a window "message" event {type:"teleq:update", data} (no reload, no flicker; up to 64 KB of JSON). With html, the page is replaced (a short reload). Only works while that page is still on screen.

Input parameters:

- `data` (object): New values for the page, delivered as message event data.
- `html` (string): Optional replacement HTML document (up to 262144 characters).
- `id` (string, required): The id returned by the show_* call that put the content up.

### `show_image` (~72 tokens)

Show an image on the TV

Show a picture on the TV, letterboxed on a black background. The image must be reachable on the public internet over https://.

Input parameters:

- `title` (string): Optional caption (up to 120 characters).
- `url` (string, required): Public https:// URL of a JPEG, PNG, WebP or GIF image.

### `show_queue` (~75 tokens)

Show several photos and videos

Show up to 50 photos and videos one after another: each photo stays for its duration_s (default 8 s), each video plays to the end. The viewer can skip with ←/→ on the remote. Public https:// links only. Returns an id.

Input parameters:

- `items` (array, required): The photos and videos in order.

### `play_video` (~128 tokens)

Play a video on the TV

Play a video on the TV in full screen inside TeleQ. Works with direct video files (.mp4, .webm, .mkv) and HLS (.m3u8) or DASH (.mpd) streams over public https://. For YouTube, Rutube, VK Video, Netflix and other services use open_in_app instead. Use `playback` afterwards to pause, resume or seek.

Input parameters:

- `title` (string): Optional title shown on the TV (up to 120 characters).
- `url` (string, required): Public https:// URL of the video file or stream.

### `open_in_app` (~243 tokens)

Open a video service on the TV

Open an episode, a cartoon, a film, a music video or a channel in the TV's own app for that service: YouTube, YouTube Kids, Rutube, VK Video, Kinopoisk, ivi, Okko, Wink, START, PREMIER, KION, more.tv, Smotrim, MEGOGO, Netflix, Prime Video, Disney+, Max, Apple TV, Twitch, Vimeo, Dailymotion, Crunchyroll, Pluto TV, Tubi. Find the official link with web search first (in the TV's language, see tv_status). The service's app then plays it (TeleQ leaves the screen; the user returns with Back/Home). Official sources only.

Input parameters:

- `start_s` (integer): Optional (YouTube): start this many seconds in.
- `title` (string): Optional title, for the notice on the TV (up to 120 characters).
- `url` (string, required): https:// link to the video, episode, series, playlist or channel page on one of the listed services (e.g. https://www.youtube.com/watch?v=…, https://rutube.ru/video/…/).

### `notify` (~58 tokens)

Show a short notice on the TV

Show a short notice for a few seconds on top of whatever is on screen, without interrupting a video. Up to 200 characters, at most one every 10 seconds.

Input parameters:

- `text` (string, required): The notice (up to 200 characters).

### `screen_snapshot` (~68 tokens)

See the TV screen

Get a picture (at most 1280 px wide) of what TeleQ is showing right now, to check that your content fits and looks right. Only TeleQ's own content an assistant put up is captured, never other apps or the user's own photos; video frames may come out black.

### `playback` (~58 tokens)

Control video playback

Control the video that is playing on the TV: play, pause, seek to a position, or stop.

Input parameters:

- `action` (string, required): What to do.
- `position_s` (number): Seconds from the start. Required when action is "seek".

### `clear_screen` (~22 tokens)

Clear the TV screen

Stop whatever is being shown and return the TV to its idle screen.

### `link_tv` (~114 tokens)

Link a TV

Link this computer with a TV running TeleQ on the same Wi-Fi. Ask the user to open TeleQ on the TV, choose Linked devices → Link an assistant, and read you the 9-digit code. Only needed once per TV (or after it was unlinked).

Input parameters:

- `code` (string, required): The 9-digit code shown on the TV.
- `tv_address` (string): Optional: the TV's address on the home network (like 192.168.1.20), when several TVs are found.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/max4et-teleq/teleq-mcp#diagnostics

## Score history

- 2026-11-21: 76
- 2026-11-20: 75
- 2026-11-19: 75
- 2026-11-18: 74
- 2026-11-17: 74
- 2026-11-16: 73
- 2026-11-15: 73
- 2026-11-14: 72
- 2026-11-13: 72

## Common questions

### What is the TeleQ TV MCP server?

TeleQ TV is an MCP server listed in the public MCP registry as io.github.max4et/teleq. Show text, slides, images, video and live HTML pages on your TV through the TeleQ app. This page covers its npm package (teleq-mcp).

### Is the TeleQ TV MCP server safe to use?

TeleQ TV scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TeleQ TV MCP server expose?

TeleQ TV exposes 16 tools: tv_status, show_text, show_slides, slides_control, show_html, and 11 more. Their descriptions and schemas cost roughly 1,753 tokens of context every time the server is loaded.

### Is the TeleQ TV MCP server still maintained?

TeleQ TV is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the TeleQ TV MCP server under?

TeleQ TV declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the TeleQ TV MCP server?

VerifyMCP ran 16 checks on TeleQ TV, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/teleq-mcp
- Socket report: https://socket.dev/npm/package/teleq-mcp
- Repository: https://github.com/max4et/teleq-ai
- Website: https://teleq.online/ai/
- Changelog RSS feed: https://verifymcp.io/servers/max4et-teleq/teleq-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/max4et-teleq/teleq-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/max4et-teleq/teleq-mcp.json
- HTML version of this page: https://verifymcp.io/servers/max4et-teleq/teleq-mcp
