# Shortform Kit (remote · shortformkit.com)

Transcribe, read and download public Reels, TikToks and YouTube videos, plus sourced creator data

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `shortformkit.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/diegobruegger-prog-shortformkit/shortformkit.md), [page](https://verifymcp.io/servers/diegobruegger-prog-shortformkit/shortformkit)

## Channel facts

- Endpoint: `https://shortformkit.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-10-18.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1779 tokens (~197/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 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 Shortform Kit MCP server?

Shortform Kit is a hosted endpoint at https://shortformkit.com/mcp, so there is nothing to install locally. 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 --transport http diegobruegger-prog-shortformkit 'https://shortformkit.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "diegobruegger-prog-shortformkit": {
      "url": "https://shortformkit.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "diegobruegger-prog-shortformkit": {
      "type": "http",
      "url": "https://shortformkit.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.diegobruegger-prog-shortformkit]
url = "https://shortformkit.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "diegobruegger-prog-shortformkit": {
      "type": "remote",
      "url": "https://shortformkit.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add diegobruegger-prog-shortformkit --url 'https://shortformkit.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  diegobruegger-prog-shortformkit:
    url: "https://shortformkit.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "diegobruegger-prog-shortformkit": {
      "Transport": "http",
      "Url": "https://shortformkit.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add diegobruegger-prog-shortformkit -t streamable-http -u 'https://shortformkit.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "diegobruegger-prog-shortformkit": {
      "type": "http",
      "url": "https://shortformkit.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-10-18 (score 73, +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.

### 2026-10-17 (score 72, 0)

- [security] Tool “get_video_info” rewrote its description, which is the text the model reads

### 2026-10-16 (score 72, +9)

- [security improvement] Authorization: unverified → partial
- [security] Tool “creator_monetization” rewrote its description, which is the text the model reads
- [security] Tool “download_media” rewrote its description, which is the text the model reads
- [security] Tool “estimate_youtube_earnings” rewrote its description, which is the text the model reads
- [security] Tool “get_video_info” rewrote its description, which is the text the model reads
- [security] Tool “loudness_and_subtitles” rewrote its description, which is the text the model reads
- [security] Tool “social_video_specs” rewrote its description, which is the text the model reads
- [security] Tool “transcribe_video” rewrote its description, which is the text the model reads
- [security] Tool “youtube_channel_id” rewrote its description, which is the text the model reads
- [security] Tool “youtube_thumbnail_trends” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 36% → 100%
- [functional] Schema quality: good → excellent
- [cosmetic] “creator_monetization” reworded the description of “country”
- [cosmetic] “creator_monetization” reworded the description of “niche”
- [cosmetic] “creator_monetization” reworded the description of “platform”
- [cosmetic] “creator_monetization” reworded the description of “topic”
- [cosmetic] “download_media” reworded the description of “at”
- [cosmetic] “download_media” reworded the description of “end”
- [cosmetic] “download_media” reworded the description of “kind”
- [cosmetic] “download_media” reworded the description of “quality”
- [cosmetic] “download_media” reworded the description of “start”
- [cosmetic] “download_media” reworded the description of “url”
- [cosmetic] “estimate_youtube_earnings” reworded the description of “monthly_views”
- [cosmetic] “estimate_youtube_earnings” reworded the description of “niche”
- [cosmetic] “estimate_youtube_earnings” reworded the description of “shorts”
- [cosmetic] “get_video_info” reworded the description of “url”
- [cosmetic] “loudness_and_subtitles” reworded the description of “name”
- [cosmetic] “loudness_and_subtitles” reworded the description of “topic”
- [cosmetic] “social_video_specs” reworded the description of “format”
- [cosmetic] “social_video_specs” reworded the description of “platform”
- [cosmetic] “transcribe_video” reworded the description of “end”
- [cosmetic] “transcribe_video” reworded the description of “language”
- [cosmetic] “transcribe_video” reworded the description of “start”
- [cosmetic] “transcribe_video” reworded the description of “translate_to_english”
- [cosmetic] “transcribe_video” reworded the description of “url”
- [cosmetic] “youtube_channel_id” reworded the description of “query”
- [cosmetic] “youtube_thumbnail_trends” reworded the description of “niche”
- [cosmetic] Tool “creator_monetization” changed its title: Creator monetization data
- [cosmetic] Tool “download_media” changed its title: Download media
- [cosmetic] Tool “estimate_youtube_earnings” changed its title: Estimate YouTube earnings
- [cosmetic] Tool “get_video_info” changed its title: Read video info
- [cosmetic] Tool “loudness_and_subtitles” changed its title: Loudness and subtitle standards
- [cosmetic] Tool “social_video_specs” changed its title: Social video specs 2026
- [cosmetic] Tool “transcribe_video” changed its title: Transcribe video
- [cosmetic] Tool “youtube_channel_id” changed its title: Find YouTube channel ID
- [cosmetic] Tool “youtube_thumbnail_trends” changed its title: YouTube thumbnail trends

### 2026-10-15 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 62, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-12 (score 61)

First indexed and scored.

## MCP tools (9)

### `get_video_info` (~154 tokens)

Read video info

Read the metadata of a public Instagram, YouTube, TikTok, X, Facebook or Pinterest post without downloading it. Returns platform, title, uploader, duration in seconds, available video heights, whether it has video/audio, gallery size, caption, hashtags and thumbnail URL. Use it first to check a link or pick a quality; use download_media to get the file and transcribe_video for the spoken words. Shares the website's limit of 30 requests per minute.

Input parameters:

- `url` (string, required): Link to a public post or video, e.g. https://www.instagram.com/reel/..., https://www.tiktok.com/@user/video/..., https://youtu.be/... Private posts and login-only content fail.

### `download_media` (~348 tokens)

Download media

Create a temporary download of a public post. Returns a job object with status and, when done, download_url (valid 15 minutes) plus job_status_url to poll if it is still running after about 100 seconds. Use kind=video for MP4, audio for MP3, image for photo posts and carousels, thumbnail for the cover, frame for a still at one timestamp. For the spoken text use transcribe_video instead. Videos up to 4 hours; only for content the user owns or may use.

Input parameters:

- `at` (string): Timestamp of the still for kind=frame. Time as '1:05', '0:01:05' or seconds ('65').
- `end` (string): Optional end of the section, must be after start. Time as '1:05', '0:01:05' or seconds ('65').
- `kind` (string): What to save: video (MP4), audio (MP3), image (photo/carousel), thumbnail (cover image) or frame (one still, needs 'at').
- `quality` (integer): Maximum video height in pixels, e.g. 720, 1080, 2160. Omit for the best available. Only for kind=video.
- `start` (string): Optional start of a section to cut. Time as '1:05', '0:01:05' or seconds ('65').
- `url` (string, required): Link to a public post or video, e.g. https://www.instagram.com/reel/..., https://www.tiktok.com/@user/video/..., https://youtu.be/... Private posts and login-only content fail.

### `transcribe_video` (~288 tokens)

Transcribe video

Transcribe the speech of a public video, Reel, TikTok or Short with Whisper on the server. Returns the plain text plus segments with start and end times; waits up to 4 minutes, otherwise returns job_status_url to poll. Use it for captions, quotes, summaries or hooks; use get_video_info if you only need the written caption. Up to 20 minutes of audio per run, one transcription at a time server-wide, so cut long videos with start/end.

Input parameters:

- `end` (string): Optional end of the part to transcribe. Time as '1:05', '0:01:05' or seconds ('65').
- `language` (string): Spoken language as ISO 639-1 code (en, de, es, pt, fr, ja ...). Omit to auto-detect; setting it improves accuracy for short clips.
- `start` (string): Optional start of the part to transcribe. Time as '1:05', '0:01:05' or seconds ('65').
- `translate_to_english` (boolean): true returns an English translation instead of the original language.
- `url` (string, required): Link to a public post or video, e.g. https://www.instagram.com/reel/..., https://www.tiktok.com/@user/video/..., https://youtu.be/... Private posts and login-only content fail.

### `youtube_channel_id` (~113 tokens)

Find YouTube channel ID

Resolve a YouTube channel to its permanent channel ID (UC...). Returns channel ID, name, handle, channel URL and the RSS feed URL. Use it when an API, embed, RSS reader or analytics tool needs the UC ID; any video link of the channel works too. Not for statistics like subscriber counts.

Input parameters:

- `query` (string, required): @handle (e.g. @mkbhd), channel URL (youtube.com/@name, /c/, /user/) or any video or Shorts URL of the channel.

### `social_video_specs` (~165 tokens)

Social video specs 2026

Look up 2026 upload specs for Instagram, TikTok, YouTube, Facebook, X, LinkedIn, Pinterest, Snapchat and Threads: aspect ratio, resolution, max length, file size, caption and hashtag limits, each row with official source links, plus recent spec changes. Use it before exporting or cropping a video for a platform. Offline data, no network calls; empty filters return every row.

Input parameters:

- `format` (string): Format filter, substring: Reels, Stories, Feed, Shorts, Long-form, Spotlight ... Empty = all formats of the platform.
- `platform` (string): Platform name filter, case-insensitive substring: Instagram, TikTok, YouTube, Facebook, X, LinkedIn, Pinterest, Snapchat, Threads. Empty = all platforms.

### `creator_monetization` (~228 tokens)

Creator monetization data

Look up sourced 2026 creator-income data. topic=programs lists monetization programs with eligibility (subscribers, watch hours, views) and status; rpm_by_niche and rpm_by_country give earnings per 1,000 views as low, high and median; engagement_benchmarks gives typical engagement rates; sponsorship_rates gives price ranges per post. Every row carries its sources. Use it to answer 'how much does X pay' or 'what do I need to monetize'; for a concrete earnings estimate from a view count use estimate_youtube_earnings instead. Offline data, max 40 rows.

Input parameters:

- `country` (string): Optional country filter for rpm_by_country: ISO code (US, DE, IN) or English name.
- `niche` (string): Optional niche filter for rpm_by_niche and sponsorship_rates, substring: finance, tech, gaming, beauty, education ...
- `platform` (string): Optional platform filter, substring: YouTube, TikTok, Instagram, Facebook, X, Snapchat ...
- `topic` (string): Which table to read.

### `loudness_and_subtitles` (~171 tokens)

Loudness and subtitle standards

Look up delivery standards for audio and captions. topic=loudness_targets gives integrated loudness (LUFS) and true-peak limits for Spotify, Apple Music, YouTube, Netflix, Prime Video, EBU R128, ATSC A/85, podcasts and social video; subtitle_standards gives characters per line, lines, reading speed and timing rules (Netflix, BBC and others); frame_rates_timecode explains frame rates and drop-frame timecode. Every value sourced. Use it when mixing, exporting or captioning for a platform. Offline data, max 40 rows.

Input parameters:

- `name` (string): Optional filter, case-insensitive substring across the row, e.g. Netflix, Spotify, podcast, 29.97.
- `topic` (string): Which table to read.

### `youtube_thumbnail_trends` (~118 tokens)

YouTube thumbnail trends

Get this week's measured thumbnail trends of the most-viewed new YouTube videos in 10 niches: share of thumbnails with faces, text and big text, brightness, dominant colours, title length, plus top example videos. Without a niche it returns the overall stats and the list of niches. Use it when designing or reviewing a thumbnail; the data refreshes weekly.

Input parameters:

- `niche` (string): One of gaming, vlog, fitness, finance, food, tech, travel, education, podcast, beauty. Empty = overview of all niches.

### `estimate_youtube_earnings` (~134 tokens)

Estimate YouTube earnings

Estimate YouTube ad revenue for a channel from its monthly views. Returns the RPM range in USD, monthly and yearly USD ranges, the model used and a link to the interactive calculator. Ads only, no sponsorships or memberships. Use creator_monetization for the underlying RPM tables and program requirements.

Input parameters:

- `monthly_views` (number, required): Views per month, e.g. 250000.
- `niche` (string): Content niche, drives the ad rate. Ignored when shorts=true.
- `shorts` (boolean): true = views are YouTube Shorts views (pooled Shorts revenue, much lower RPM).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/diegobruegger-prog-shortformkit/shortformkit#diagnostics

## Score history

- 2026-10-18: 73
- 2026-10-17: 72
- 2026-10-16: 72
- 2026-10-15: 63
- 2026-10-14: 62
- 2026-10-13: 62
- 2026-10-12: 61

## Common questions

### What is the Shortform Kit MCP server?

Shortform Kit is an MCP server listed in the public MCP registry as io.github.diegobruegger-prog/shortformkit. Transcribe, read and download public Reels, TikToks and YouTube videos, plus sourced creator data. This page covers its hosted endpoint (https://shortformkit.com/mcp).

### Is the Shortform Kit MCP server safe to use?

Shortform Kit scores 73 out of 100 on VerifyMCP. 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 Shortform Kit MCP server expose?

Shortform Kit exposes 9 tools: get_video_info, download_media, transcribe_video, youtube_channel_id, social_video_specs, and 4 more. Their descriptions and schemas cost roughly 1,719 tokens of context every time the server is loaded.

### Does the Shortform Kit MCP server require authentication?

No. We connected to Shortform Kit without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Shortform Kit MCP server still maintained?

Shortform Kit is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://shortformkit.com/mcp
- Repository: https://github.com/diegobruegger-prog/shortformkit-mcp
- Website: https://shortformkit.com/mcp-server/
- Changelog RSS feed: https://verifymcp.io/servers/diegobruegger-prog-shortformkit/shortformkit.xml
- Changelog JSON feed: https://verifymcp.io/servers/diegobruegger-prog-shortformkit/shortformkit.json
- HTML version of this page: https://verifymcp.io/servers/diegobruegger-prog-shortformkit/shortformkit