mcp-video-frames — Video MCP Server

An MCP server that lets image-only models look at video: frames with timecodes, plus measurable video properties.

Available Tools

The server provides these tools:

• view_frames - Sample a time range and return frames as images, each preceded by its timecode
• video_info - Container metadata, optionally with a whole-file scene/silence/loudness scan

The model you are talking to must accept image input. Without it, the returned frames are dropped or degraded to text.

This is a local server: it is not hosted anywhere, and a client has to be pointed at it. See Self-Hosted below.

Install from PyPI

pip install mcp-video-frames      # or run it without installing: uvx mcp-video-frames

That installs one console script, and the console script is the server. Point a client at it:

{
  "mcpServers": {
    "video-frames": { "command": "mcp-video-frames" }
  }
}

With no subcommand and piped stdio it speaks MCP; on a terminal it prints help instead of hanging. mcp-video-frames doctor checks the environment it will run in.

This path expects ffmpeg and ffprobe on PATH. If you would rather have them installed into a private virtual environment, along with a ready-made client config, use Self-Hosted below instead.

Self-Hosted

Installs nothing into your system Python: dependencies go into the project's own .venv/, and the client config points at that interpreter directly.

1. Clone the repository

git clone https://github.com/Azzy-H/mcp-video-frames.git
cd mcp-video-frames

2. Generate the virtual environment and the client config

python setup_mcp.py

setup_mcp.py only does three things:

1. creates .venv/ in this directory (run it with any Python 3.10+ interpreter);
2. installs the two runtime dependencies from requirements.txt into that .venv/;
3. writes mcp-config.json, with the paths already filled in.

Options:

python setup_mcp.py --max-images 12      # match your client's image limit
python setup_mcp.py --print              # print the config only; write nothing
python setup_mcp.py --ffmpeg <path>      # ffmpeg is not on PATH

If ffmpeg is missing the script offers to download a prebuilt build into .venv/ (Windows), to point at one you installed, or to skip. Nothing is ever installed system-wide.

3. Check the environment before wiring it up

.venv/Scripts/python run_server.py doctor     # Windows
.venv/bin/python     run_server.py doctor     # macOS / Linux

This reports the ffmpeg/ffprobe paths and versions, whether the required filters are present, and whether the cache directory is writable — naming whatever is missing rather than leaving you to guess. It finds a venv-local ffmpeg on its own, so nothing has to be exported first.

test_server.py goes further and speaks real MCP to the server over stdio, so the whole path can be verified before any client is configured:

.venv/Scripts/python test_server.py connect <video file path>   # Windows
.venv/bin/python     test_server.py connect <video file path>   # macOS / Linux

It checks the handshake, the tool list, the 2n + 1 content-block ordering, whether a single-frame request comes back as PNG, and that an over-limit request is refused — and that stdout stays clean for the JSON-RPC stream.

4. Add this MCP server

Merge the generated mcp-config.json into your client's config. If an mcpServers section already exists, just add the video-frames entry to it. run_server.py puts src/ on sys.path itself, so no PYTHONPATH is needed and nothing has to be pip installed anywhere.

Replace /path/to/mcp-video-frames with the actual path to this repository on your system. On Windows the interpreter is .venv\Scripts\python.exe.

Uninstall: delete .venv/ and remove that config entry. Nothing else was written.

Requirements

• Python 3.10 or newer
• ffmpeg and ffprobe. setup_mcp.py installs (or downloads) them into the project's own .venv/, and the server looks for them beside its own interpreter first, then on PATH — so a venv-local install needs no FFMPEG_PATH to be exported. ffmpeg is required; without ffprobe, metadata falls back to parsing ffmpeg's own header output (fewer fields), and doctor says so explicitly
• A client model that accepts image input

Tools

view_frames

Samples a time range and returns an interleaved timecode + image sequence. Set start and end to the same value to look at a single moment.

The result is 2n + 1 content blocks:

text:  {"n":0,"t":0.0}
image: <frame 0>
text:  {"n":1,"t":1.0}
image: <frame 1>
...
text:  {"video":"...","frames":12,"range":[0.0,11.0],"interval":1.0,
        "format":"jpeg","max_edge":768,"clamped":false,"cached":9,
        "limits":{"max_images_per_call":20,"max_image_bytes":10485760,
                  "max_total_bytes":41943040}}

The block order is load-bearing: an image without its timecode cannot be reasoned about in time. clamped reports whether the range was trimmed to the video's length, cached how many frames came from disk, and limits repeats the budget in force so the numbers do not have to be discovered by being rejected.

A range defaults to jpeg because at equal edge length it is about an order of magnitude smaller, which fits many more frames inside a client's byte budget. Ask for a single frame as png when detail matters.

Over a limit the call fails: nothing is truncated and the interval is never widened. Silently coarsening the sampling grid would invalidate the caller's assumption about time precision, so the whole call fails instead. If any single frame fails validation, no frames are returned.

video_info

Returns video metadata. detail="basic" reads container headers only and returns immediately; detail="full" adds an exhaustive whole-file scan for scene cuts, silences and EBU R128 loudness.

{
  "path": "", "sha256": "", "size_bytes": 0,
  "duration": 0.0, "fps": 0.0, "width": 0, "height": 0,
  "video_codec": "", "pix_fmt": "",
  "color_range": "", "color_space": "", "is_hdr": false,
  "audio_tracks": [], "subtitle_tracks": [], "chapters": [],
  "detail": "full",
  "scene_cuts": [1.23, 5.67],
  "silences": [{"start": 12.0, "end": 14.5, "duration": 2.5}],
  "loudness": {"integrated_lufs": -23.0, "true_peak_dbfs": -1.2, "lra": 5.0},
  "scan": {"ffmpeg_version": "", "computed_at": "", "cached": false}
}

With detail="basic" the scene_cuts / silences / loudness / scan fields are absent rather than empty — "no value" and "not scanned" mean different things. The first full call scans the whole file; later calls reuse the cache. force=true recomputes.

Configuration

Environment variables take precedence over defaults.

MCP_VIDEO_MAX_IMAGES caps how many frames one call may return. Set it to match your client: limits differ between clients, and while too low is merely conservative, too high makes the entire batch unusable. max_frames defaults to 12 and may be raised only up to this limit.

The effective limits are also stated in the tool descriptions and repeated in every view_frames result, so a caller can see them without being rejected first.

CLI

The same package ships a CLI for troubleshooting and batch work:

mcp-video-frames doctor               # environment self-check
mcp-video-frames info video.mp4       # basic metadata
mcp-video-frames scan video.mp4       # pre-build the full scan
mcp-video-frames scan --dir ./videos  # process a whole directory
mcp-video-frames frames video.mp4 --start 0 --end 5   # frames, as content-block JSON
mcp-video-frames cache --stats        # cache usage
mcp-video-frames cache --prune        # evict cache entries

Without installing the project (Self-Hosted above), use the launcher for the same subcommands:

.venv/Scripts/python run_server.py doctor            # Windows
.venv/bin/python     run_server.py info video.mp4    # macOS / Linux