Model Context Protocol
Your agent can write the code.
It has never seen a good launch video.
STEALSHOT indexes 160 launch videos, product films, demos and podcast intros frame by frame. Every frame has been described for its craft, how it is framed, lit, typeset and cut, so an agent can search by what a shot looks like rather than by title. 15,461 frames, 108 brands.
Install
Claude Code
claude mcp add stealshot --scope user --transport http https://stealshot.com/api/mcp
Cursor
{
"mcpServers": {
"stealshot": {
"url": "https://stealshot.com/api/mcp"
}
}
}Codex
codex mcp add stealshot --transport http https://stealshot.com/api/mcp
No API key and no account. The library is public and every tool is read only.
6 tools
search_frames
Search the frame library by what is actually IN and TRUE OF a shot. This is the main way in. Every frame has been described by a vision model, so plain language works: 'presenter against a dark backdrop with the UI floating beside them', 'code on a light background with huge negative space', 'title card that opens on the wordmark'. Combine free text with the filters to narrow by craft.
query · technique · subject · surface · shot_type · tone · brand · launch_only · opening_only · limit
find_pattern
Given a technique or a plain-language move, gather the EVIDENCE for it across different videos: one best example per brand, plus how widespread it is. This is the tool for 'is this a real convention or did one video do it once', and for building an argument rather than a single reference. Always prefer this over search_frames when the question is about a pattern rather than a picture.
technique · query · limit
list_techniques
List the technique vocabulary the library actually uses, with how many frames and how many distinct videos use each. Call this before search_frames when you want to filter precisely, or to answer 'what moves are common in launch videos'. A technique used by many DIFFERENT videos is a convention; one used many times inside a single video is that video's habit, so both counts are returned.
contains · min_videos · limit
get_video
The full anatomy of one video: its measurements plus a shot-by-shot walk through its described frames in time order. Use this after search_frames when a single reference is worth studying properly, or to answer 'how is this video actually built'. Prefer it over many search calls on the same title.
video_id · title · max_frames
compare_brands
Compare how two or more brands cut their videos: pace, how much of the frame is a face, how dark they shoot, and their most-used techniques. Use for 'how does Linear's launch style differ from OpenAI's'.
brands
library_stats
What is actually in the library right now: counts, the brands with the most indexed videos, and how much of it has been described. Call this first if you need to know whether a question is answerable, and to avoid claiming coverage the corpus does not have.
no arguments
Ask it things like
- How do the strongest launch videos open? Give me the first five seconds.
- Is a centred wordmark on black a real convention or does one video do it?
- Find presenter shots where the UI floats beside the person, not behind them.
- Compare how OpenAI and Cursor cut a launch video.
- I have one person, one room and one afternoon. What do I shoot?