video-context-mcp-server 0.50.0-beta → 0.50.2-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.
package/README.md CHANGED
@@ -40,7 +40,7 @@ After install, two equivalent CLI commands are available: `video-context-mcp` (f
40
40
  ### Updating & version check
41
41
 
42
42
  ```bash
43
- npm ls -g --depth=0 video-context-mcp-server # installed version
43
+ npm ls -g video-context-mcp-server # installed version
44
44
  npm outdated -g video-context-mcp-server # check for updates
45
45
  npm install -g video-context-mcp-server@latest # update
46
46
  ```
@@ -308,14 +308,14 @@ When an audio key is missing or an audio API call fails at runtime, tools automa
308
308
 
309
309
  Set `VIDEO_MCP_DEFAULT_PROVIDER=gemini`, `qwen`, `kimi`, or `mimo` to change the default.
310
310
 
311
- > **ℹ️ Large local files with GLM or Qwen:** Both providers have a 10–12 MB base64 limit for local files. When a file exceeds this limit, the server first tries to fall back to an upload-capable provider (Gemini or Kimi) if one is available in the fallback chain. Frame-based analysis (evenly-spaced keyframes sent as images) is used only as a **last resort** when no upload-capable provider is available, or when all upload-capable providers fail at runtime — no configuration needed. For the highest quality with large local videos, set up the optional **S3 relay** (below) — GLM and Qwen will receive a presigned URL to the full video, bypassing the limit entirely and taking priority over both fallbacks.
311
+ > **ℹ️ Large local files with GLM, Qwen, or MiMo:** All three providers have a 10–12 MB base64 limit for local files. When a file exceeds this limit, the server first tries to fall back to an upload-capable provider (Gemini or Kimi) if one is available in the fallback chain. Frame-based analysis (evenly-spaced keyframes sent as images) is used only as a **last resort** when no upload-capable provider is available, or when all upload-capable providers fail at runtime — no configuration needed. For the highest quality with large local videos, set up the optional **S3 relay** (below) — GLM, Qwen, and MiMo will receive a presigned URL to the full video, bypassing the limit entirely and taking priority over both fallbacks.
312
312
 
313
313
  <details open>
314
- <summary><strong>Automatic S3 relay: bypass the 10 MB local file limit with Qwen and GLM</strong></summary>
314
+ <summary><strong>Automatic S3 relay: bypass the 10 MB local file limit with GLM, Qwen, and MiMo</strong></summary>
315
315
 
316
- **GLM-4.6V** and **Qwen3.5** both accept direct video URLs, but base64-encoding a local file caps out at **10–12 MB**. Above that limit, the server first tries to fall back to an upload-capable provider (Gemini or Kimi) if one is available, then falls back to **frame-based analysis** as a last resort. For the best results on large local videos, set `AWS_S3_BUCKET` — the server uploads the full video to S3 and passes a presigned URL to GLM/Qwen, bypassing the base64 limit entirely and taking priority over both fallbacks. No manual upload step needed.
316
+ **GLM-4.6V**, **Qwen3.5**, and **MiMo-V2 Omni** all accept direct video URLs, but base64-encoding a local file caps out at **10–12 MB**. Above that limit, the server first tries to fall back to an upload-capable provider (Gemini or Kimi) if one is available, then falls back to **frame-based analysis** as a last resort. For the best results on large local videos, set `AWS_S3_BUCKET` — the server uploads the full video to S3 and passes a presigned URL to GLM, Qwen, and MiMo, bypassing the base64 limit entirely and taking priority over both fallbacks. No manual upload step needed.
317
317
 
318
- **Why it works**: Qwen and GLM require the server to serve `Content-Length` and `Content-Type` headers alongside the video. AWS S3 provides these automatically.
318
+ **Why it works**: GLM, Qwen, and MiMo require the server to serve `Content-Length` and `Content-Type` headers alongside the video. AWS S3 provides these automatically.
319
319
 
320
320
  **One-time setup**
321
321
 
@@ -486,9 +486,9 @@ vmcp cache clear:all --yes # skip confirmation
486
486
 
487
487
  ### Video Summarization
488
488
 
489
- | Variable | Description | Default |
490
- | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------- |
491
- | `VIDEO_MCP_MAX_FRAMES` | Max keyframes for `summarize_video` (GLM/Kimi/Qwen/MiMo only; Gemini uploads full video). **Free**: clamped 5–50. **Pro**: default 100; set `0` for uncapped. Either way, trailing frames are automatically dropped if the total payload exceeds the provider's size limit (12 MB for GLM, 10 MB for Qwen/MiMo, 80 MB for Kimi). | `50` free / `100` pro |
489
+ | Variable | Description | Default |
490
+ | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------- |
491
+ | `VIDEO_MCP_MAX_FRAMES` | Max keyframes for `summarize_video` (GLM/Qwen/MiMo always; Kimi only when video > 100 MB; Gemini always uploads full video). **Free**: clamped 5–50. **Pro**: default 100; set `0` for uncapped. Either way, trailing frames are automatically dropped if the total payload exceeds the provider's size limit (12 MB for GLM, 10 MB for Qwen/MiMo, 80 MB for Kimi's frame fallback). | `50` free / `100` pro |
492
492
 
493
493
  ### Qwen
494
494
 
@@ -1,2 +1,2 @@
1
- export declare const VERSION = "0.50.0-beta";
1
+ export declare const VERSION = "0.50.2-beta";
2
2
  //# sourceMappingURL=version.d.ts.map
@@ -1,3 +1,3 @@
1
1
  // Auto-generated by scripts/sync-version.ts — do not edit
2
- export const VERSION = '0.50.0-beta';
2
+ export const VERSION = '0.50.2-beta';
3
3
  //# sourceMappingURL=version.js.map
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "video-context-mcp-server",
3
- "version": "0.50.0-beta",
3
+ "version": "0.50.2-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",