Repository avatar
Other Tools
v0.1.2
active

media-context

io.github.mollymogi/media-context

Keep images, video & audio out of coding agent contexts — local FFmpeg + zero extra API cost.

Documentation

media-context (mctx)

context-mode + rtk for Images, Video & Audio

Keep heavy media out of your coding agent's context window — local-first, zero extra API cost, works across Antigravity (agy), Claude Code, Codex, OpenCode, dsh, and any CLI.

🌐 English  |  简体中文

Python 3.9+ Zero Dependencies Zero Extra API Cost MCP Compatible MIT License


Context & Token Savings (Before vs. After)

media-context Before vs After Context and Token Benchmark

Metric (30 Images + 10 Audio Clips · 12 Turns)Before (Raw Read / read_file)After (With mctx)Delta (Δ)
Main Session Context Size~410,000 tokens~32,000 tokens-378,000 tokens (-92.2%)
Media Payload Pinned in History40 files (8.54 MB)0 files (0 B)-100% media bloat
Avg Time-to-First-Token (TTFT)285–324 s (~5.2 min/step)3–5 s-306 s/step (77× faster)
12-Turn Cumulative Model Wait~62 min~48 s-61.2 min saved
Extra Vision API BillingExtra API keys / per-token bill$0 (FFmpeg + your CLI sub)$0 extra

Why does this happen? Tools like rtk and context-mode protect you from large text logs, but every time an agent directly Reads a PNG, extracted video frame, or WAV clip into the main conversation, that heavy multimodal payload stays pinned in context for every subsequent turn.


How It Works (3-Stage Funnel)

Raw Video / Images / Audio
   │
   ├─► L1 · Local Zero-Token Tools (FFmpeg / FFprobe / Local Whisper)
   │        • mctx probe      → compact JSON metadata + audio silence/clipping + black-frame checks
   │        • mctx sheet      → stitch video or N frames into 1 timestamped contact sheet JPEG
   │        • mctx shrink     → downscale huge 4K PNGs into lightweight JPEGs
   │        • mctx transcribe → offline local Whisper transcription (mlx-whisper / whisper-cpp)
   │
   ├─► L2 · Stateless Subscription CLI Worker + Auto-Fallback + SQLite Cache ($0 extra API)
   │        • mctx inspect    → spawns a disposable, stateless worker using your existing CLI
   │                            (agy / claude -p / codex exec / opencode run), inspects the
   │                            compressed sheet, caches by sha256 in SQLite, and returns
   │                            ONLY concise text to your main session.
   │
   └─► L3 · Cross-Client PreToolUse Guard Hook
            • mctx hook run   → blocks accidental raw media Read/read_file (or auto-shrinks),
                                with automatic MCTX_BYPASS=1 for internal workers.
  • Zero Python third-party dependencies (Python 3.9+ stdlib + ffmpeg/ffprobe).
  • One core, three interfaces: CLI (mctx), stdio MCP server (mctx mcp), and PreToolUse hook (mctx hook).

Quick Start

1. Install

git clone https://github.com/mollymogi/media-context.git
cd media-context
pip install -e .
# Or with pipx:
# pipx install .

Check your local toolchain and detected subscription CLIs:

mctx doctor

2. CLI Usage (works in dsh, scripts, and every agent)

# Zero-token metadata + audio volume/silence + video black-frame check
mctx probe clip.mp4 --audio --black

# Compress a video or folder of 30 frames into 1 timestamped 3x3 contact sheet
mctx sheet clip.mp4 --grid 3x3 --width 1280
mctx sheet ./frames/ --grid 3x3

# Shrink a single large screenshot
mctx shrink hero_4k.png --max-side 1024

# Stateless visual QA using your existing CLI subscription (zero main-session leak, SQLite cached)
mctx inspect clip.mp4 -q "Check if the character's hands deform or if any frame is corrupted."
mctx inspect ./frames/ -q "Compare lighting consistency across frames" --backend claude

# Offline local audio transcription (auto-detects mlx_whisper / whisper-cli / whisper)
mctx transcribe voiceover.wav -l zh

# Check cumulative bytes & tokens saved
mctx stats

3. Connect via MCP (Antigravity, Claude Code, Codex, OpenCode, Magpie Hub)

Register mctx mcp as a stdio MCP server (only 6 compact tools exposed):

{
  "mcpServers": {
    "media-context": {
      "command": "mctx",
      "args": ["mcp"]
    }
  }
}

4. Default Models & Automatic Quota/Capacity Fallback

When the primary model hits quota limits (429), capacity congestion (503 No capacity), or auth expiry (401), mctx inspect automatically switches to the next available target in your fallback chain, places the failing model into a local SQLite cooldown (default 5 min), and prints a clear [mctx:fallback] notice:

mctx config init            # creates ~/.config/media-context/config.json
mctx config show            # view active fallback chain & cooldowns
mctx config reset-cooldown  # clear cooldowns immediately

Example ~/.config/media-context/config.json:

{
  "cooldown_seconds": 300,
  "fallback_chain": [
    {"backend": "agy", "model": "gemini-4-neon-medium"},
    {"backend": "claude", "model": "sonnet"},
    {"backend": "codex", "model": ""},
    {"backend": "opencode", "model": ""}
  ]
}

5. Optional PreToolUse Guard Hook

Generate ready-to-paste hook snippets for your client:

mctx hook config antigravity --mode block
mctx hook config claude --mode block
mctx hook config claude --mode shrink
  • --mode block: blocks raw image/audio/video Read / read_file and guides the agent to mctx probe / sheet / inspect (whitelisted mctx_sheet_* and mctx_shrink_* artifacts pass through).
  • --mode shrink: blocks raw audio/video, and transparently downscales oversized images before reading.

Environment Variables

VariableDescription
MCTX_FALLBACK_CHAINComma-separated fallback override (e.g. agy:gemini-4-neon-medium,claude:sonnet,codex)
MCTX_CONFIGCustom config JSON path (default: ~/.config/media-context/config.json)
MCTX_COOLDOWN_SECONDSCooldown window after quota/capacity errors (default: 300)
MCTX_BACKEND / MCTX_MODELSingle backend / model override
MCTX_HOMECache & SQLite directory (default: ~/.cache/media-context)
MCTX_BYPASS=1Bypass PreToolUse hook (automatically set inside mctx inspect workers)

License

MIT

PYPI
media-context
Install Command
pip install media-context
Runtime: uvx