Skip to main content
Glama
mhe8mah

WebP Batch Converter

by mhe8mah

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.

🌟 Features

  • 🖼️ Batch conversion of PNG, JPG, and JPEG files to WebP

  • 🌍 Cross-platform support (macOS, Linux, Windows)

  • Multi-threaded processing for fast conversions

  • 🎛️ Flexible options including quality control, lossless mode, and metadata preservation

  • 📊 Detailed reporting with file sizes and savings statistics

  • 🔧 Dual engine support - prefers Google's cwebp, falls back to Sharp

  • 🎯 MCP integration for use in AI-powered development environments

Related MCP server: GPT Image MCP Server

📦 Installation

Global Installation

npm install -g webp-batch-mcp

Local Development

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

Docker

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

🚀 Usage

Command Line Interface

node dist/cli.js [options]

Options

  • --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

Examples

# 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

MCP Server

The MCP server exposes a single tool: convert_to_webp

Tool Parameters

{
  "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)
}

⚙️ How to Add This Server in Cursor

  1. Clone and build the project:

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

  2. Navigate to FeaturesMCP

  3. Add a new server configuration:

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

  2. The convert_to_webp tool will be available in your AI conversations

🔧 Technical Details

Conversion Strategy

  1. Primary Engine: Google's cwebp tool (included in libwebp-tools)

    • Fastest performance

    • Best compression

    • Full feature support

  2. Fallback Engine: Sharp (Node.js)

    • Pure JavaScript implementation

    • No external dependencies

    • Cross-platform compatibility

Output Behavior

  • Default: Creates .webp files 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

Performance

  • Utilizes all CPU cores by default

  • Processes images concurrently using p-limit

  • Provides real-time progress feedback

  • Reports detailed conversion statistics

🛠️ Development

Building

npm run build

Testing

npm test

Development Mode

npm run dev

📊 Test Results

Verified with real web images:

  • JPEG (35KB → 17KB): 51% space savings

  • PNG (7.9KB → 2.8KB): 65% space savings

  • Overall: 53% average compression

📋 Dependencies

Runtime

  • @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

Development

  • typescript - Type safety

  • tsup - Fast TypeScript bundler

  • jest - Testing framework

📄 License

MIT License - see LICENSE file for details.

🤝 Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Add tests for new functionality

  4. Ensure all tests pass

  5. Submit a pull request

🆘 Support

For issues and feature requests, please use the GitHub issue tracker.

Available Tools

1 tool
convert_to_webpA

Batch convert images (PNG, JPG, JPEG) to WebP format with customizable options. Recursively scans directories and provides detailed conversion reports.

ParametersJSON Schema
NameRequiredDescriptionDefault
srcNoSource directory to scan for images (default: current directory).
qualityNoWebP quality (0-100, default: 75)
losslessNoUse lossless encoding (recommended for PNG images)
overwriteNoReplace original files with WebP versions
threadsNoNumber of concurrent conversions (default: 2)
preserveMetaNoPreserve EXIF and ICC metadata
flatNoOutput all WebP files to specified directory (optional)

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses key behavioral traits like batch processing, recursive directory scanning, and detailed reports, but lacks information on permissions, error handling, rate limits, or what the reports contain. It's adequate but has gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with core functionality and efficiently uses two sentences with zero waste. Every phrase ('batch convert', 'customizable options', 'recursively scans', 'detailed conversion reports') adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and a 7-parameter tool with high schema coverage, the description is moderately complete. It covers the tool's scope and key behaviors but lacks details on outputs (reports), error cases, or advanced usage, leaving room for improvement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional meaning beyond implying batch and recursive behavior, which is partially covered by parameters like 'src' and 'threads'. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('batch convert', 'recursively scans') and resources ('images (PNG, JPG, JPEG) to WebP format'), and distinguishes it by mentioning batch processing and directory scanning. No siblings exist, but it's still specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives (e.g., single-file conversion tools or other formats). It mentions 'customizable options' but doesn't specify scenarios or exclusions, leaving usage context implied at best.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

TDQS

A3.6/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as batch converting images to WebP format, making it impossible for an agent to misselect among multiple options.

Naming Consistency5/5

Since there is only one tool, naming consistency is inherently perfect. The tool name 'convert_to_webp' follows a clear verb_noun pattern, and with no other tools to compare, there are no inconsistencies or deviations in naming conventions.

Tool Count2/5

A single tool is generally too few for a server's purpose, as it limits functionality and can feel thin. For a batch conversion tool, additional operations like listing files, checking formats, or managing settings might be expected to provide a more complete surface, making the count borderline inadequate.

Completeness3/5

The tool covers the core conversion functionality well, but there are notable gaps in the surface. For a batch conversion domain, missing operations might include checking image formats, listing files before conversion, or providing status updates, which could lead to agent workarounds or inefficiencies in handling the workflow.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mhe8mah/webp-batch-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server