What image formats are supported?
JPEG, PNG, WebP, and AVIF are supported.
@InhiblabCore
基本信息
A high-performance image compression microservice based on MCP (Modal Context Protocol)
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-image-compression": {
"command": "docker",
"args": [
"build",
"-t",
"mcp-image-compression",
"."
]
}
}
}`urls` (strings): URLs of images to compress
Compressed images url
mcp-image-compression is a high-performance image compression microservice built on the MCP (Modal Context Protocol) architecture. It helps developers optimize image resources for websites and applications to improve loading speed and user experience.
Configure the server via NPX in your MCP client settings, specifying the command npx -y @inhiblab-core/mcp-image-compression and setting the environment variable IMAGE_COMPRESSION_DOWNLOAD_DIR to your download directory. Use the image_compression tool with parameters urls, quality, and format to compress images. You can also build from source using Docker.
JPEG, PNG, WebP, and AVIF are supported.
No, it works offline – no internet connection is needed.
Set the `quality` parameter (integer, 0–100) when calling the `image_compression` tool.
Use NPX with the command `npx -y @inhiblab-core/mcp-image-compression` and provide the `IMAGE_COMPRESSION_DOWNLOAD_DIR` environment variable.
Yes, the `urls` parameter accepts multiple image URLs for batch processing.

Break down any TikTok or Instagram Reels ad and rewrite it for your product, right inside Claude, Cursor, or ChatGPT. Hooks, UGC scripts, and CPM. Free, no API key.

Design your mobile app UI with AI, then have your coding agent build the real app from it.

Public Mangii MCP metadata (ai.mangii/manga). Remote Streamable HTTP at mcp.mangii.ai.

Official LinkedIn, Slack and GitHub profile photo specs with sources, headshot style guides by use and industry, and a free 0-100 headshot audit. No API key needed.

A remote MCP server from GOJI, a full-service digital agency in Melbourne, Australia. Nine tools over published material: a 104-term plain-English glossary, a 14-chapter guide to AI visibility, seven long-form guides inc
评论