video-context-mcp-server 0.18.2-beta → 0.18.4-beta

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +4 -2
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -15,6 +15,8 @@ Video Context MCP Server is a Model Context Protocol (MCP) server that gives MCP
15
15
  - 🎯 **Smart Video Handling** — Extracts keyframes from long videos to reduce token usage (when not using Gemini)
16
16
  - ⭐ **Pro tier** — audio-enhanced analysis, extended frame extraction, and multi-platform video downloads. [Learn more ↓](#-pro)
17
17
 
18
+ **[Check demo here](https://www.youtube.com/watch?v=vv4ojD5_67M)**
19
+
18
20
  ## 🔓 Pro
19
21
 
20
22
  The free tier covers all core functionality. A **pro license** unlocks four power features:
@@ -22,7 +24,7 @@ The free tier covers all core functionality. A **pro license** unlocks four powe
22
24
  | Feature | Free Tier | Pro |
23
25
  | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------- | --------------------------------- |
24
26
  | **🔊 Audio-enhanced analysis** — Auto-transcribes a video's audio track and injects the transcript into AI prompts, giving `analyze_video` and `summarize_video` richer, more accurate results. Controlled by `AUDIO_ENHANCE_VIDEO_ANALYSIS`.<br />**Note**: The `transcribe_video` tool itself is available to all users — this feature specifically enhances the _analysis_ tools by injecting the transcript automatically. | Disabled | ✅ Enabled |
25
- | **🖼️ Extended frame extraction** — Raise the keyframe cap for long or complex videos beyond the free-tier limit. Controlled by `VIDEO_MCP_MAX_FRAMES`. | Capped at 50 | Default 100; set `0` for uncapped |
27
+ | **🖼️ Extended frame extraction** — Raise the keyframe cap used by `summarize_video` for long or complex videos beyond the free-tier limit. Controlled by `VIDEO_MCP_MAX_FRAMES`. | Capped at 50 | Default 100; set `0` for uncapped |
26
28
  | **🌐 Platform video downloads** — Analyze videos directly from YouTube, Vimeo, TikTok, and hundreds of other yt-dlp-supported platforms without downloading manually.<br />**Note**: Local files and direct `http(s)://` video file URLs (e.g., `https://example.com/video.mp4`) work for all users — no license needed. This gate only applies to platform URLs handled by yt-dlp (e.g., YouTube, Vimeo, TikTok links). | YouTube only | All platforms |
27
29
  | **📺 Extended download resolution** — Raise the yt-dlp download resolution cap beyond 720p for higher-quality platform video downloads. Controlled by `YT_DLP_MAX_RESOLUTION`. | Capped at 720p | Uncapped |
28
30
 
@@ -373,7 +375,7 @@ When a provider's API key is missing, the tool automatically falls back to the n
373
375
  | `MOONSHOT_API_KEY` | Moonshot AI API key for Kimi K2.5 | Optional (required if using Kimi) |
374
376
  | `GEMINI_API_KEY` | Google API key for Gemini 3 Flash Preview | Optional (required if using Gemini) |
375
377
  | `VIDEO_MCP_DEFAULT_PROVIDER` | Default video backend (`gemini`, `glm`, `kimi`) | Optional (default: `glm`) |
376
- | `VIDEO_MCP_MAX_FRAMES` | Max frames for summarization (GLM/Kimi only). **Pro**: unset/empty defaults to 100; set to `0` for uncapped (size guard still enforced); any value ≥ 5 is used as-is. **Free**: clamped to 5–50; `0` or unset defaults to 50. | Optional (default: 50 for free / 100 for pro; free users clamped to 5–50) |
378
+ | `VIDEO_MCP_MAX_FRAMES` | Max keyframes extracted by `summarize_video` for long videos (GLM/Kimi only). **Pro**: unset/empty defaults to 100; set to `0` for uncapped (size guard still enforced); any value ≥ 5 is used as-is. **Free**: clamped to 5–50; `0` or unset defaults to 50. | Optional (default: 50 for free / 100 for pro; free users clamped to 5–50) |
377
379
  | `DEEPGRAM_API_KEY` | Deepgram API key for `transcribe_video` | Optional (required if using Deepgram) |
378
380
  | `ASSEMBLYAI_API_KEY` | AssemblyAI API key for `transcribe_video` | Optional (required if using AssemblyAI) |
379
381
  | `GROQ_API_KEY` | Groq API key for Whisper transcription via `transcribe_video` | Optional (required if using Groq) |
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "video-context-mcp-server",
3
- "version": "0.18.2-beta",
3
+ "version": "0.18.4-beta",
4
4
  "description": "A Model Context Protocol server that gives GitHub Copilot the ability to understand and analyze video content",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",