Shortform Kit MCP Server

Install Shortform Kit MCP server

claude mcp add --transport http shortformkit https://shortformkit.com/mcp

{
  "mcpServers": {
    "shortformkit": {
      "url": "https://shortformkit.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "shortformkit": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://shortformkit.com/mcp"
      ]
    }
  }
}

{
  "servers": {
    "shortformkit": {
      "type": "http",
      "url": "https://shortformkit.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "shortformkit": {
      "serverUrl": "https://shortformkit.com/mcp"
    }
  }
}

Context tax

Connecting this server adds ~2,140 tokens of tool definitions to every model turn (moderate, 9 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure

Input prices as of 2026-10-06. Excludes your own prompt and output.

Tools (9)

• download_mediahttp407 tok

  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.

• transcribe_video330 tok

  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.

• creator_monetization288 tok

  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.

• loudness_and_subtitles218 tok

  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.

• estimate_youtube_earnings202 tok

  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.

• social_video_specs186 tok

  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.

• get_video_info177 tok

  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.

• youtube_thumbnail_trends137 tok

  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.

• youtube_channel_id136 tok

  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.

Freshness

Not enough public signals yet to judge maintenance.

1. Last commit (default branch)

   2026-10-16 · 3d ago · GitHub

2. Latest release

   no data · GitHub

3. Package published

   no data · npm/PyPI

4. Registry entry updated

   2026-10-15 · 3d ago · official registry · v1.0.1

How it compares in Images, Video & Audio

Against the most-starred images, video & audio servers we index. Token cost is per model turn, measured from each server's live tool list.