Skip to content
Video Assets Server

Video Assets Server quick start

Video Assets Server searches free stock video sites at once and tells you, for every clip, whether you can use it in a commercial video. NASA’s Image and Video Library and Scientific Visualization Studio, Wikimedia Commons and the Internet Archive are searched directly; Pexels, Pixabay, Coverr, Mixkit, Europeana, the Library of Congress and the paid libraries (Shutterstock, Adobe Stock, Getty Images, Storyblocks…) get a deep link with the same search. Results cover b-roll, backgrounds, nature, cities, people, aerials, space, science and archive films, with resolution, orientation, frame rate and length where known, a poster, a preview and a licence verdict.

The public server at https://video.shep.bot is a free, non-commercial service and needs no account or API key.

Pick how you want to use it

You want to… Use Start here
Browse, watch and download footage yourself The web search /search
Turn a shot list into a b-roll edit (OTIO, ffmpeg, Remotion) The sequence builder /sequence
Let Claude Code, Cursor, Copilot or another agent find footage The MCP server at https://video.shep.bot/mcp Coding agents & MCP
Call it from a script, a render pipeline or a backend The REST API REST API guide
Search and download from a terminal The CLI (npx video-assets-server) CLI
Explore every endpoint and try requests The interactive reference API reference

Connect your agent (30 seconds)

For Claude Code, run this once:

claude mcp add --transport http video https://video.shep.bot/mcp

Then ask for what you need:

Find three 4K clips of ocean waves at sunset that I can use in a client ad.
Tell me their licences and the credit lines I need.

Cursor, VS Code, Windsurf, Codex CLI, Gemini CLI and the Claude apps take the same URL. See Coding agents & MCP for each one.

Or call the API

# Vertical ocean clips, at least 1080p, cleared for commercial use
curl "https://video.shep.bot/v1/search?q=ocean+waves&orientation=portrait&min_resolution=1080&commercial=true&limit=5"

# Details, renditions, the credit line and a watch URL for one result
curl "https://video.shep.bot/v1/clips/nasa%3AGSFC_20161212_Tidal_m12450_Magnetic"

# Download the 1080p rendition (a redirect to the file on NASA's servers)
curl -L -o tides.mp4 "https://video.shep.bot/v1/clips/nasa%3AGSFC_20161212_Tidal_m12450_Magnetic/download?height=1080"

What a search returns

Every search returns three things:

  • results: clips merged from all sources and ranked by how well they match. Each has an id like nasa:<nasa-id>, a category (nature.ocean, space.launch, archive.newsreel…), styles (timelapse, slow-motion…), orientation, width, height, fps, durationSec and year when known, a posterUrl and a previewUrl that play in a browser straight from the source, a license with a verdict and an editorial flag, an attribution line when credit is required, and downloadable.
  • filters: what the server understood. Words like “4k”, “vertical”, “10s”, “60fps” or “timelapse” in the query become filters.
  • providers: one status line per source (ok, error, timeout, skipped or link). Sites that can’t be searched automatically come back as link with a searchUrl that runs the same search on their site.

A slow or broken source never fails the search.

No video through the server

Video Assets Server never streams, proxies or re-hosts video. It searches the sources, reads their metadata, decides a licence verdict and writes credit files. Everything that moves pictures comes straight from the source’s servers:

  • Posters and previews in the search grid load from the source’s CDN (images-assets.nasa.gov, upload.wikimedia.org, archive.org, svs.gsfc.nasa.gov).
  • The player in a clip’s detail view plays the source’s file (the watch URL from GET /v1/clips/{id}).
  • Downloads (/v1/clips/{id}/download) answer 302 with the file’s URL on the source.
  • Sequences (POST /v1/sequences) return OTIO, ffmpeg and Remotion files whose media URLs point at the sources.

So the server stays small and cheap, the sources see real viewers, and nothing is redistributed.

Licences, in one line each

  • Commercial use OK (yes): use it, no credit needed.
  • Commercial use OK with credit (yes-with-credit): use it and credit the source with the attribution line.
  • Restricted, Needs a paid licence or releases, Unclear (restricted, clearance-required, check-terms): read the terms first.
  • Non-commercial only (no): study and personal projects, not ads or client work.
  • Editorial (license.editorial: true): people, insignia or brands without releases. News and documentary yes, advertising no.

commercial=true keeps only the first two verdicts. The full explanation is in Video licences explained.

For AI agents reading this

Machine-readable entry points:

Coding agents & MCP →

AI agent? This page is also available as markdown.