MCP server for TinyPNG
Usage
Use bun or node to run the server
- Install dependencies and build
pnpm i
pnpm build
- Edit the
mcp.jsonfile
{
"mcpServers": {
"tinypng": {
"command": "bun", // or "node"
"args": ["/path/to/tinypng-mcp-server/src/index.ts"], // or "dist/index.js"
"env": {
"TINYPNG_API_KEY": "your-tinypng-api-key"
}
}
}
}
Installing via Smithery
To install TinyPNG MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @aiyogg/tinypng-mcp-server --client claude
Tools
- Compress local image
{
name: 'compress_local_image',
description: 'Compress a local image file',
inputSchema: {
type: 'object',
properties: {
imagePath: {
type: 'string',
description: 'The ABSOLUTE path to the image file to compress',
example: '/Users/user/Downloads/image.jpg',
},
outputPath: {
type: 'string',
description: 'The ABSOLUTE path to save the compressed image file',
example: '/Users/user/Downloads/image_compressed.jpg',
},
outputFormat: {
type: 'string',
description: 'The format to save the compressed image file',
enum: SUPPORTED_IMAGE_TYPES,
example: 'image/jpeg',
},
},
required: ['imagePath'],
},
}
- Compress remote image
{
name: 'compress_remote_image',
description: 'Compress a remote image file by giving the URL of the image',
inputSchema: {
type: 'object',
properties: {
imageUrl: {
type: 'string',
description: 'The URL of the image file to compress',
example: 'https://example.com/image.jpg',
},
outputPath: {
type: 'string',
description: 'The ABSOLUTE path to save the compressed image file',
example: '/Users/user/Downloads/image_compressed.jpg',
},
outputFormat: {
type: 'string',
description: 'The format to save the compressed image file',
enum: SUPPORTED_IMAGE_TYPES,
example: 'image/jpeg',
},
},
required: ['imageUrl'],
},
}
TinyPNG MCP Server
Project Details
- aiyogg/tinypng-mcp-server
- Apache License 2.0
- Last Updated: 4/11/2025
Recomended MCP Servers
Config files for my GitHub profile.
A Model Context Protocol server for AI vision analysis using Gemini Vision API
A Model Context Protocol (MCP) server implementation for running Locust load tests. This server enables seamless integration of...
Simple MCP Server w/ Shell Exec. Connect to Local via Ngrok, or Host Ubuntu24 Container via Docker
3D Maps for OpenSceneGraph / C++14
Use mcp to manage containerd(developing)
A Model Context Protocol (MCP) server for interacting with Kong Konnect APIs, allowing AI assistants to query and...
A working pattern for SSE-based MCP clients and servers
JIRA MCP Server Implementation in Python
BloodHound-MCP-AI is integration that connects BloodHound with AI through Model Context Protocol, allowing security professionals to analyze Active...





