WebP Batch Converter

A Model Context Protocol (MCP) server for batch converting images to WebP format with cross-platform support. Works seamlessly with MCP-aware IDEs like Cursor.

- 🖼️Batch conversionof PNG, JPG, and JPEG files to WebP
- 🌍Cross-platformsupport (macOS, Linux, Windows)
- ⚡Multi-threadedprocessing for fast conversions
- 🎛️Flexible optionsincluding quality control, lossless mode, and metadata preservation
- 📊Detailed reportingwith file sizes and savings statistics
- 🔧Dual engine support- prefers Google's cwebp, falls back to Sharp
- 🎯MCP integrationfor use in AI-powered development environments

git clone https://github.com/mhe8mah/webp-batch-mcp.git cd webp-batch-mcp npm install npm run build

docker build -t webp-batch . docker run -v /path/to/images:/data webp-batch

- --src <dir>- Source directory to scan (default: current directory)
- --quality <0-100>- WebP quality setting (default: 75)
- --lossless- Use lossless encoding (recommended for PNG)
- --overwrite- Replace original files with WebP versions
- --threads <n>- Number of concurrent conversions (default: CPU count)
- --preserve-meta- Preserve EXIF and ICC metadata
- --flat <dir>- Output all WebP files to specified directory

# Convert all images in current directory node dist/cli.js # High quality conversion of specific directory node dist/cli.js --src ./photos --quality 95 --preserve-meta # Lossless conversion with overwrite node dist/cli.js --src ./images --lossless --overwrite # Batch process to output directory node dist/cli.js --src ./input --flat ./output --threads 8

The MCP server exposes a single tool:convert_to_webp

{ "src": "string", // Source directory (default: ".") "quality": "number", // Quality 0-100 (default: 75) "lossless": "boolean", // Lossless mode (default: false) "overwrite": "boolean", // Replace originals (default: false) "threads": "number", // Concurrent threads (default: CPU count) "preserveMeta": "boolean", // Keep metadata (default: false) "flat": "string" // Output directory (optional) }

git clone https://github.com/mhe8mah/webp-batch-mcp.git cd webp-batch-mcp npm install npm run build

- Open Cursor Settings
- Navigate toFeatures→MCP
- Add a new server configuration:

{ "mcpServers": { "webp-batch": { "command": "node", "args": ["/path/to/webp-batch-mcp/dist/server.js"] } } }

- Restart Cursor
- Theconvert_to_webptool will be available in your AI conversations
-

Primary Engine: Google'scwebptool (included in libwebp-tools)

- Fastest performance
- Best compression
- Full feature support

- Pure JavaScript implementation
- No external dependencies
- Cross-platform compatibility

- Default: Creates.webpfiles alongside originals
- Overwrite mode: Replaces originals with WebP versions
- Flat mode: Outputs all WebP files to specified directory
- Metadata preservation: Maintains EXIF and ICC profiles when requested

- Utilizes all CPU cores by default
- Processes images concurrently using p-limit
- Provides real-time progress feedback
- Reports detailed conversion statistics

- JPEG (35KB → 17KB): 51% space savings
- PNG (7.9KB → 2.8KB): 65% space savings
- Overall: 53% average compression

- @modelcontextprotocol/sdk- MCP server framework
- sharp- Image processing fallback
- chalk- Colorized terminal output
- commander- CLI argument parsing
- glob- File pattern matching
- p-limit- Concurrency control

- typescript- Type safety
- tsup- Fast TypeScript bundler
- jest- Testing framework

MIT License - see LICENSE file for details.
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Ensure all tests pass
- Submit a pull request

For issues and feature requests, please use theGitHub issue tracker.

Official MCP server for Very Good FFmpeg