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 +8 -8
- package/dist/generated/version.d.ts +1 -1
- package/dist/generated/version.js +1 -1
- package/package.json +1 -1
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
|
|
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npm outdated -g video-context-mcp-server # check for updates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
|
|
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
|
|
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
|
|
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
|
|
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
|
|
490
|
-
| ---------------------- |
|
|
491
|
-
| `VIDEO_MCP_MAX_FRAMES` | Max keyframes for `summarize_video` (GLM/
|
|
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.
|
|
1
|
+
export declare const VERSION = "0.50.2-beta";
|
|
2
2
|
//# sourceMappingURL=version.d.ts.map
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "video-context-mcp-server",
|
|
3
|
-
"version": "0.50.
|
|
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",
|