Skip to main content
Glama

mcp-movingimagearchive

MCP server for Moving Image Archive: a searchable library of shots cut from public-domain archival films, all free to reuse. Inspired by a reply from the site's creator, Cova, welcoming the idea of an MCP server for it. This is an unofficial project.

Tools

Tool

What it does

Site equivalent

search_clips

Semantic shot search by visual description, with color / aspect ratio / year filters. Empty query browses every shot.

Search box + Filter

list_sources

All source films, sorted featured / recent / by title (direction: "asc" for A–Z; the default desc gives Z–A), plus archive totals

Gallery

get_source

One film: synopsis, provenance & rights, full-film URL, shot list with per-shot URLs

/sources/<slug>

list_collections

Curated themed collections

Collections

get_collection

Shots in one collection

/collection/<slug>

download

Save a single shot, the full film, or a shot/time range (trimmed with ffmpeg) to a local MP4. Defaults to ~/Downloads, never overwrites, cancellable

Download buttons, shift-click range download

Every shot result includes clipDownloadUrl (the shot MP4) and sourceDownloadUrl (the full film).

Related MCP server: FrameThrower MCP Server

Setup

Requires Node ≥ 20 (≥ 22.18 only to run pnpm test, which runs the .ts files directly). ffmpeg on PATH is only needed for range downloads.

git clone https://github.com/JoaquimCassano/mcp-movingimagearchive.git
cd mcp-movingimagearchive
pnpm install && pnpm build

Claude Code:

claude mcp add --scope user movingimagearchive -- node /absolute/path/to/mcp-movingimagearchive/dist/index.js

Claude Desktop / other clients:

{
  "mcpServers": {
    "movingimagearchive": { "command": "node", "args": ["/absolute/path/to/mcp-movingimagearchive/dist/index.js"] }
  }
}

How it talks to the site

These are the site's own endpoints and page sizes. The MCP tools return smaller pages (see each tool's limit) and paginate with offset/nextOffset.

  • POST /api/search {query, color, aspectRatio, yearMin?, yearMax?, offset} — shot search (24/page)

  • GET /api/clips?color&aspectRatio&offset&yearMin&yearMax — browse shots (100/page)

  • GET /api/sources?sort&direction&offset&limit — gallery (max 100/page)

  • GET /api/clips/<id>/download, GET /api/sources/<slug>/download — redirects to the MP4

  • Source and collection pages have no JSON endpoint; their data is read from the Next.js RSC payload (RSC: 1 header). If the site's markup changes, get_source / get_collection / list_collections are the tools that may break.

Range downloads replicate the site's shift-click feature: the site trims the full film in the browser between the first shot's start and the last shot's end; here ffmpeg does the same, using HTTP range requests so only that part of the film is fetched (a 300 MB excerpt of a 10 GB film needs ~300 MB of disk, not 10 GB).

pnpm test   # offline parser checks

The site's Feedback form is intentionally not exposed: its endpoint only accepts submissions from the website itself.

Available Tools

6 tools
downloadDownload footageA

Save footage to a local MP4 (never overwrites an existing file). Pass exactly one of clipId (a single shot) or sourceSlug (the full film). To get only part of it, add startSeconds and/or endSeconds (relative to that shot or film), or, with sourceSlug, fromShot/toShot (1-based, inclusive, like shift-click on the site). Ranges need ffmpeg on PATH; only that part is fetched and it is re-encoded for frame-accurate cuts. If you only need a link, use the URLs returned by the other tools instead.

Inputs: clipId, toShot, fromShot, endSeconds, +3 more.

get_collectionGet collectionB
Read-only

Get the shots in one curated collection, with timing, source film and download links.

Inputs: slug (required), limit, offset.

get_sourceGet film detailsA
Read-only

Get one source film: title, year, running time, synopsis, provenance & rights (original producer, collection, original Internet Archive link), full-film download URL and its shot list with per-shot download URLs.

Inputs: slug (required), limit, offset.

list_collectionsList collectionsA
Read-only

List the archive's curated, themed collections of shots (e.g. Cats, Film Countdowns, Space Flight) with their slugs and shot counts.

Inputs: no named parameters.

list_sourcesList films (gallery)B
Read-only

List the source films in the archive (the site's Gallery), with archive totals. Each film has a slug for get_source and a full-film download link.

Inputs: sort, limit, offset, direction.

search_clipsSearch shotsA
Read-only

Search the archive for individual shots by a visual description (semantic/CLIP search, e.g. 'red sunset over water', 'crowd at a 1930s world fair'). Leave query empty to browse all shots in archive order. Returns shot timing, source film and direct MP4 links for the shot and the full film. Pass nextOffset back as offset for more.

Inputs: color, limit, query, offset, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: search shots, list source films, get one source film, list curated collections, get one collection, and download footage. The download tool explicitly disambiguates itself from URL-returning tools. No two tools overlap in a confusing way.

    Naming Consistency4/5

    Most names follow a clear verb_noun snake_case pattern: search_clips, list_sources, get_source, list_collections, get_collection. The lone exception is download, which lacks a noun but is still unambiguous. This is mostly consistent with a minor deviation.

    Tool Count5/5

    Six tools is well-scoped for a moving image archive: search, browse films, inspect a film, browse collections, inspect a collection, and download. Each tool earns its place without redundancy or obvious missing surface area.

    Completeness4/5

    The surface covers searching clips, browsing and inspecting source films and collections, and downloading clips or full films. Minor gaps exist, such as no dedicated get_clip-by-id tool and no direct collection-level download, but these are workable via search results and existing download options.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables search across videos you've watched via transcripts, on-screen text, and frames, citing exact timestamps. Point it at videos, channels, or playlists; it indexes everything locally and answers queries with deep links to the exact second.
      3
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables connecting any MCP client to a cinematography reference library of 5,489 films. Allows searching film frames by look, mood, or craft attributes, and refining through similar-frame discovery.
      3
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to index videos locally once and then browse a compact text map of shots, transcript, silences and visual embeddings, so they can query moments, cut dead air, apply edit scripts, render with ffmpeg and run QA checks without spending tokens on frames. Pixels are only fetched when the agent explicitly peeks at labeled contact sheets.
      9
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Gives AI agents video perception by turning screen recordings, films and URLs into timestamped structured evidence: ordered UI states and transitions, per-screen OCR, shots, camera motion, palettes, on-screen text and speech, all cached locally with no API keys. Includes drill-down tools to zoom into intervals, crop full-resolution frames, diff two moments, and search on-screen text and speech across everything watched.
      15
      3
      MIT