What is Vibestudio

VibeStudio is a high-performance, headless video editing server designed for AI assistants. It is built entirely in Bash and utilizes the Model Context Protocol (MCP) to provide advanced FFmpeg functionality without any runtime dependencies.

Use cases

Use cases for VibeStudio include converting video formats, trimming and merging videos, adding subtitles, extracting audio from videos, and applying video filters, all of which can be executed as simple shell commands.

How to use

To use VibeStudio, simply execute the provided Bash commands in a local shell. The commands are lightweight and designed to be integrated seamlessly into AI workflows, allowing for efficient media editing operations.

Key features

Key features of VibeStudio include zero runtime overhead, full self-containment in Bash scripts, no reliance on frameworks or servers, seamless integration with MCP-compatible assistants, and debug-friendly CLI commands with clear inputs and outputs.

Where to use

VibeStudio can be used in various fields such as media production, content creation, AI-driven applications, and any scenario requiring automated video and audio editing without the need for complex setups.

VibeStudio is a high-performance, headless video editing server designed for AI assistants. Built entirely in Bash and based on the Model Context Protocol (MCP), it delivers advanced FFmpeg functionality with zero runtime dependencies.

💡 Note: Heads up! Make sure your volume’s on

https://github.com/user-attachments/assets/7fe093ff-0abf-43af-b2fa-34a64ebe1fe8

It exposes powerful media editing tools—video, audio, and more—as lightweight, local shell commands. This makes it ideal for AI agents needing reliable, fast, and traceable tool-based workflows.

Why Choose VibeStudio?

• Zero runtime overhead – no Python, Node.js, or other runtimes required
• Fully self-contained – pure Bash scripts, easy to inspect and audit
• No frameworks – no servers, RPC layers, or glue code
• MCP-compatible – integrates seamlessly with any assistant that supports tool calls
• Debug-friendly – transparent, traceable CLI commands with clear inputs/outputs

Features

Video Operations

• Format Conversion: Convert between video formats (MP4, AVI, MKV, MOV, etc.)
• Video Trimming: Extract specific portions of videos with frame-accurate precision
• Video Merging: Seamlessly concatenate multiple videos
• Video Resizing: Change video dimensions for any platform
• Subtitle Addition: Burn subtitles directly into videos
• Frame Extraction: Export video frames as high-quality images
• Image to Video: Create videos from image sequences
• Video Filters: Apply professional filters (blur, sharpen, rotate, color correction)
• Thumbnail Generation: Create preview images automatically

Audio Operations

• Audio Extraction: Extract audio tracks from videos in any format
• Format Conversion: Convert between audio formats (MP3, AAC, WAV, FLAC, OGG)
• Audio Trimming: Cut audio files with precision
• Volume Normalization: Normalize audio levels for consistent playback

Analysis Tools

• Media Information: Get detailed metadata about any media file

Prerequisites

1. Bash shell (version 4.0+)

2. jq for JSON processing

   # macOS
   brew install jq
   
   # Ubuntu/Debian
   sudo apt-get install jq
   
   # CentOS/RHEL
   sudo yum install jq
   

3. FFmpeg with common codecs

   # macOS
   brew install ffmpeg
   
   # Ubuntu/Debian
   sudo apt-get install ffmpeg
   
   # CentOS/RHEL
   sudo yum install ffmpeg
   

Installation

1. Clone the repository

   git clone https://github.com/wizenheimer/vibestudio.git
   cd vibestudio
   

2. Make scripts executable

   chmod +x ffmpegserver.sh mcpserver_core.sh
   

Available Tools

get_media_info

Get detailed information about a media file.

{
  "input_file": "path/to/media.mp4"
}

convert_video

Convert video to different format or codec.

extract_audio

Extract audio track from video.

trim_media

Trim video or audio to specified duration.

{
  "input_file": "input.mp4",
  "output_file": "output.mp4",
  "start_time": "00:01:30",
  "duration": "00:00:30"
}

merge_videos

Concatenate multiple videos.

{
  "input_files": [
    "video1.mp4",
    "video2.mp4",
    "video3.mp4"
  ],
  "output_file": "merged.mp4"
}

add_subtitles

Burn subtitles into video.

{
  "input_file": "video.mp4",
  "subtitle_file": "subtitles.srt",
  "output_file": "video_with_subs.mp4"
}

resize_video

Change video dimensions.

{
  "input_file": "input.mp4",
  "output_file": "output.mp4",
  "width": 1280,
  "height": 720
}

extract_frames

Extract frames as images.

create_video_from_images

Create video from image sequence.

apply_video_filter

Apply FFmpeg filters.

{
  "input_file": "input.mp4",
  "output_file": "output.mp4",
  "filter": "hflip,blur=5"
}

generate_thumbnail

Create thumbnail from video.

convert_audio

Convert audio format.

normalize_audio

Normalize audio volume.

{
  "input_file": "input.mp3",
  "output_file": "normalized.mp3"
}

Usage with VS Code

1. Update VS Code settings.json

   {
     "mcp": {
       "servers": {
         "vibestudio": {
           "type": "stdio",
           "command": "/absolute/path/to/vibestudio-mcp/ffmpegserver.sh",
           "args": [],
           "env": {}
         }
       }
     }
   }
   

2. Use with GitHub Copilot Chat

   /mcp vibestudio get_media_info {"input_file": "video.mp4"}
   /mcp vibestudio convert_video {"input_file": "input.avi", "output_file": "output.mp4"}
   

Examples

Example 1: Convert and Resize Video

# Convert AVI to MP4 and resize to 720p
echo '{"jsonrpc": "2.0", "method": "tools/call", "params": {"name": "convert_video", "arguments": {"input_file": "movie.avi", "output_file": "movie_temp.mp4"}}, "id": 1}' | ./ffmpegserver.sh

echo '{"jsonrpc": "2.0", "method": "tools/call", "params": {"name": "resize_video", "arguments": {"input_file": "movie_temp.mp4", "output_file": "movie_720p.mp4", "width": 1280, "height": 720}}, "id": 2}' | ./ffmpegserver.sh

Example 2: Extract Audio and Normalize

# Extract audio from video and normalize volume
echo '{"jsonrpc": "2.0", "method": "tools/call", "params": {"name": "extract_audio", "arguments": {"input_file": "video.mp4", "output_file": "audio_raw.mp3"}}, "id": 1}' | ./ffmpegserver.sh

echo '{"jsonrpc": "2.0", "method": "tools/call", "params": {"name": "normalize_audio", "arguments": {"input_file": "audio_raw.mp3", "output_file": "audio_normalized.mp3"}}, "id": 2}' | ./ffmpegserver.sh

Example 3: Create GIF from Video

# Extract frames and create animated sequence
echo '{"jsonrpc": "2.0", "method": "tools/call", "params": {"name": "extract_frames", "arguments": {"input_file": "video.mp4", "output_pattern": "frame_%04d.png", "fps": "10", "start_time": "00:00:05", "duration": "00:00:03"}}, "id": 1}' | ./ffmpegserver.sh

Common Video Filters

Here are some useful filters for the apply_video_filter tool:

• Blur: "blur=10" (value: 0-100)
• Sharpen: "unsharp=5:5:1.0"
• Horizontal Flip: "hflip"
• Vertical Flip: "vflip"
• Rotate 90°: "transpose=1"
• Rotate 180°: "transpose=2,transpose=2"
• Grayscale: "colorchannelmixer=.3:.4:.3:0:.3:.4:.3:0:.3:.4:.3"
• Brightness: "eq=brightness=0.1" (-1.0 to 1.0)
• Contrast: "eq=contrast=1.5" (0.0 to 2.0)
• Fade In: "fade=in:0:30" (fade in over 30 frames)
• Speed Up 2x: "setpts=0.5*PTS"
• Slow Down 2x: "setpts=2.0*PTS"

Troubleshooting

Common Issues

1. “mcpserver_core.sh: No such file or directory”

   • Solution: Download mcpserver_core.sh from the MCP Bash SDK repository
   • Run: curl -O https://raw.githubusercontent.com/wizenheimer/vibestudio/main/mcpserver_core.sh

2. “jq: command not found”

   • Solution: Install jq using your package manager
   • macOS: brew install jq
   • Linux: sudo apt-get install jq

3. “ffmpeg: command not found”

   • Solution: Install FFmpeg
   • macOS: brew install ffmpeg
   • Linux: sudo apt-get install ffmpeg

4. Permission denied errors

   • Solution: Make scripts executable
   • Run: chmod +x ffmpegserver.sh mcpserver_core.sh

5. JSON parsing errors

   • Check logs: tail -f logs/ffmpegserver.log
   • Validate JSON: echo '{"your": "json"}' | jq .

Debug Mode

Enable verbose logging by modifying the log level in ffmpegserver.sh or checking the full logs:

# Watch logs in real-time
tail -f logs/ffmpegserver.log

# Check last 50 log entries
tail -n 50 logs/ffmpegserver.log

Sanity Tests

Run these tests to ensure VibeStudio is properly installed:

Test 1: Check Core Dependencies

# Check if jq is installed
jq --version
# Expected: jq-1.6 or higher

# Check if FFmpeg is installed
ffmpeg -version
# Expected: ffmpeg version details

# Check if mcpserver_core.sh exists
ls -la mcpserver_core.sh
# Expected: File should exist with execute permissions

Test 2: Test MCP Server Initialization

# Test server initialization
echo '{"jsonrpc": "2.0", "method": "initialize", "params": {"clientInfo": {"name": "test"}}, "id": 1}' | ./ffmpegserver.sh | jq
# Expected: JSON response with serverInfo and capabilities

Test 3: List Available Tools

# List all available tools
echo '{"jsonrpc": "2.0", "method": "tools/list", "id": 2}' | ./ffmpegserver.sh | jq
# Expected: JSON response with array of 14 tools

Test 4: Test Media Info Tool (with sample file)

# First, create a test video file
ffmpeg -f lavfi -i testsrc=duration=1:size=320x240:rate=30 -f lavfi -i sine=frequency=1000:duration=1 test_video.mp4

# Test get_media_info tool
echo '{"jsonrpc": "2.0", "method": "tools/call", "params": {"name": "get_media_info", "arguments": {"input_file": "test_video.mp4"}}, "id": 3}' | ./ffmpegserver.sh
# Expected: JSON response with media information (duration, codecs, resolution)

Test 5: Test Error Handling

# Test with non-existent file
echo '{"jsonrpc": "2.0", "method": "tools/call", "params": {"name": "get_media_info", "arguments": {"input_file": "non_existent.mp4"}}, "id": 4}' | ./ffmpegserver.sh
# Expected: JSON error response with "File not found" message

# Test with invalid method
echo '{"jsonrpc": "2.0", "method": "invalid_method", "id": 5}' | ./ffmpegserver.sh
# Expected: JSON error response with code -32601

Test 6: Check Logs

# Check if logging is working
tail -n 20 logs/ffmpegserver.log
# Expected: Log entries for all the above test commands

Test 7: Full Integration Test

# Create a simple test video and process it
ffmpeg -f lavfi -i testsrc=duration=3:size=640x480:rate=30 -f lavfi -i sine=frequency=1000:duration=3 test_source.mp4

# Extract a 1-second clip
echo '{"jsonrpc": "2.0", "method": "tools/call", "params": {"name": "trim_media", "arguments": {"input_file": "test_source.mp4", "output_file": "test_trimmed.mp4", "start_time": "00:00:01", "duration": "00:00:01"}}, "id": 6}' | ./ffmpegserver.sh

# Check if output was created
ls -la test_trimmed.mp4
# Expected: File should exist with size > 0

# Clean up test files
rm -f test_video.mp4 test_source.mp4 test_trimmed.mp4

Required Files Structure

Your VibeStudio installation should have this structure:

vibestudio-mcp/
├── mcpserver_core.sh        # Core MCP server (from MCP Bash SDK)
├── ffmpegserver.sh          # VibeStudio main script
├── assets/
│   ├── ffmpegserver_config.json
│   └── ffmpegserver_tools.json
└── logs/
    └── ffmpegserver.log     # Created automatically

Limitations

• No real-time streaming support
• Sequential processing only (no parallel operations)
• File paths must be accessible from the script location
• Large files may take significant processing time
• Some advanced FFmpeg features require manual filter construction

Shoutout

• MCP Server Bash SDK
• FFmpeg

Contributing

VibeStudio welcomes contributions! Please feel free to submit issues and enhancement requests.

License

This project is licensed under the MIT License, following the original MCP Server Bash SDK.