broll-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BROLL_HOME | No | Platform data dir by default (~/Library/Application Support/broll-mcp, ~/.local/share/broll-mcp). Location for cache, keyframes and clips. The server writes nowhere else. | |
| BROLL_AGENT_MODEL | No | Model name sent in the User-Agent, as archive.org asks of AI agents. Defaults to "unspecified". | |
| BROLL_CACHE_MAX_MB | No | Keyframe cache budget in MB; older keyframes are evicted first. Defaults to 2048. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_footageA | Turn a written shot brief into up to 5 ranked archive.org video items with license, collection tier and why each matched. Page with next_cursor. Text matching runs on archive.org; ranking is local. |
| inspect_itemA | Show what is inside an archive.org item. For one video: detected scenes with a keyframe image each (paged), plus shotlist excerpt and license. For items holding many separate clips: a paged clip list with one thumbnail per clip; call again with file=. |
| extract_clipA | Cut start_s..start_s+duration_s from a remote archive.org video into a verified H.264 MP4 under BROLL_HOME/clips, with a provenance JSON beside it. Returns 3 check frames. Repeating the same cut returns the existing clip. |
| get_provenanceA | Read the provenance record of a clip (clip_id) or the license/source record of an item plus clips already cut from it (identifier). Local records only; never contacts archive.org. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| stats | Request counts by endpoint, cache contents and the active scene detector. |
TDQS
Scored across 4 tools
Each tool maps to a distinct stage: search remote footage, inspect a remote item, extract a clip locally, and read local provenance. There is minor overlap because both inspect_item and get_provenance can return license/source information for an item, but the remote-vs-local distinction is clearly stated.
All four names follow a consistent snake_case verb_noun pattern: search_footage, inspect_item, extract_clip, get_provenance. The convention is predictable and immediately readable.
Four tools are well-scoped for a focused footage search, inspection, extraction, and provenance workflow. Each tool has a clear role and none appears redundant.
The surface covers the core lifecycle from discovery through extraction and provenance, with paging and repeat-cut handling described. Minor gaps exist around managing or listing already extracted clips, but agents can work around this through provenance lookups.