@vibeframe/mcp-server 0.95.1 → 0.96.0
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 +15 -8
- package/dist/index.js +1901 -1336
- package/package.json +3 -3
package/README.md
CHANGED
|
@@ -10,7 +10,7 @@ Confirmed MCP hosts today: **Claude Desktop**, **Cursor**, **OpenCode**, and **C
|
|
|
10
10
|
|---------|---------|-----------------|
|
|
11
11
|
| MCP host (Claude Desktop / Cursor / OpenCode / Claude Code) | `@vibeframe/mcp-server` *(this)* | host calls tool by name, for example `mcp__vibeframe__build({...})` |
|
|
12
12
|
| Shell / scripts (any agent host: Codex / Aider / Gemini CLI / etc.) | `@vibeframe/cli` | `vibe init my-video && vibe build my-video && vibe render my-video` |
|
|
13
|
-
|
|
|
13
|
+
| Optional standalone agent REPL | `@vibeframe/cli` (`vibe agent`) | natural language -> CLI calls when you do not already use Claude Code/Codex/Cursor/etc. |
|
|
14
14
|
|
|
15
15
|
The tool list below is what the MCP host sees. The same operations exist as `vibe <verb> <noun>` subcommands in the CLI — see `vibe --help`.
|
|
16
16
|
|
|
@@ -77,7 +77,7 @@ Once connected, your MCP host can resolve prompts like these into typed tool cal
|
|
|
77
77
|
> *→ `init` + 3× `scene_add` + `render`*
|
|
78
78
|
|
|
79
79
|
> "Generate a cinematic backdrop image, animate it for 5 seconds, add narration"
|
|
80
|
-
> *→ `generate_image` + `
|
|
80
|
+
> *→ `generate_image` + `generate_video` + `generate_speech`*
|
|
81
81
|
|
|
82
82
|
> "Remove silent segments and add captions to my interview"
|
|
83
83
|
> *→ `edit_silence_cut` + `edit_caption`*
|
|
@@ -110,9 +110,9 @@ Tool names are MCP-side. Your host typically prefixes them (e.g. Claude shows th
|
|
|
110
110
|
|------|-------------|-----------|
|
|
111
111
|
| `generate_image` | Text-to-image | OpenAI, Google, Stability |
|
|
112
112
|
| `generate_background` | Cinematic backdrop image (video-tuned prompt) | OpenAI |
|
|
113
|
-
| `generate_video` | Text/image-to-video (long-running) |
|
|
113
|
+
| `generate_video` | Text/image-to-video (long-running) | Seedance via fal.ai, Grok, Kling, Runway, Google Veo |
|
|
114
114
|
| `generate_video_status` / `_cancel` / `_extend` | Manage long-running video jobs | (provider-specific) |
|
|
115
|
-
| `generate_motion` |
|
|
115
|
+
| `generate_motion` | Generate standalone designed motion graphics | Claude or Gemini + Remotion |
|
|
116
116
|
| `generate_speech` | Text-to-speech | ElevenLabs |
|
|
117
117
|
| `generate_music` | AI background music | Suno, ElevenLabs, Replicate MusicGen |
|
|
118
118
|
| `generate_music_status` | Poll Replicate music task | Replicate |
|
|
@@ -120,14 +120,15 @@ Tool names are MCP-side. Your host typically prefixes them (e.g. Claude shows th
|
|
|
120
120
|
| `generate_thumbnail` | AI thumbnail composition | OpenAI, Google |
|
|
121
121
|
| `generate_storyboard` | Multi-beat storyboard frames | OpenAI, Google |
|
|
122
122
|
|
|
123
|
-
### Editing (
|
|
123
|
+
### Editing (16)
|
|
124
124
|
|
|
125
125
|
| Tool | Description |
|
|
126
126
|
|------|-------------|
|
|
127
127
|
| `edit_silence_cut` | Remove silent segments (FFmpeg or Gemini) |
|
|
128
128
|
| `edit_jump_cut` | Remove filler words (Whisper) |
|
|
129
129
|
| `edit_caption` / `edit_animated_caption` | Burn styled / animated captions |
|
|
130
|
-
| `edit_text_overlay` |
|
|
130
|
+
| `edit_text_overlay` | Simple static text burn-in |
|
|
131
|
+
| `edit_motion_overlay` | Designed animated overlays or user-provided Lottie overlays |
|
|
131
132
|
| `edit_fade` | Fade in/out |
|
|
132
133
|
| `edit_grade` | Color grading |
|
|
133
134
|
| `edit_speed_ramp` | Variable-speed segments |
|
|
@@ -194,11 +195,11 @@ Tool names are MCP-side. Your host typically prefixes them (e.g. Claude shows th
|
|
|
194
195
|
| `remix_auto_shorts` | Long-form → vertical shorts |
|
|
195
196
|
| `remix_regenerate_scene` | Re-render a single scene against an existing storyboard.{yaml,json} |
|
|
196
197
|
|
|
197
|
-
###
|
|
198
|
+
### Guides (1)
|
|
198
199
|
|
|
199
200
|
| Tool | Description |
|
|
200
201
|
|------|-------------|
|
|
201
|
-
| `
|
|
202
|
+
| `guide` | Cross-host guides for motion, scene, pipeline, and architecture workflows |
|
|
202
203
|
|
|
203
204
|
> **CLI ↔ MCP sync**: `packages/mcp-server/src/tools/cli-sync.test.ts` is a vitest hook that fails CI when a CLI subcommand is added/removed/renamed without the matching MCP change. Open the test file to see the live mapping table — `null` rows mark CLI-only commands (e.g. `vibe audio list-voices`, `vibe timeline set`) that are intentionally not exposed via MCP.
|
|
204
205
|
|
|
@@ -238,6 +239,12 @@ API keys are read from the host's environment (`~/.zshrc`, MCP config `env` bloc
|
|
|
238
239
|
| `FAL_API_KEY` | Seedance image-to-video |
|
|
239
240
|
| `RUNWAY_API_SECRET` | Runway video |
|
|
240
241
|
| `KLING_API_KEY` | Kling video |
|
|
242
|
+
| `IMGBB_API_KEY` | Default temporary image host for Seedance/Kling image-to-video |
|
|
243
|
+
| `VIBE_UPLOAD_PROVIDER` | `imgbb` (default) or `s3` for temporary image uploads |
|
|
244
|
+
| `VIBE_UPLOAD_S3_BUCKET` | S3 bucket when `VIBE_UPLOAD_PROVIDER=s3` |
|
|
245
|
+
| `VIBE_UPLOAD_S3_PREFIX` | Optional S3 key prefix for temporary image uploads |
|
|
246
|
+
| `VIBE_UPLOAD_TTL_SECONDS` | Optional TTL hint for temporary upload URLs |
|
|
247
|
+
| `AWS_ACCESS_KEY_ID` / `AWS_SECRET_ACCESS_KEY` / `AWS_REGION` | S3 upload host credentials |
|
|
241
248
|
| `VIBE_PROJECT_PATH` | Default timeline JSON path for resources |
|
|
242
249
|
|
|
243
250
|
## Requirements
|