How do I get a TinyPNG API key?
The README does not explain how to obtain an API key; you must have one to set in the `TINYPNG_API_KEY` environment variable.
@aiyogg
基本信息
🧙🏻 Integrated TinyPNG MCP server, quickly use TinyPNG through LLMs.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"tinypng-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@aiyogg/tinypng-mcp-server",
"--client",
"claude"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Tinypng Mcp Server is a Model Context Protocol server that integrates with the TinyPNG API to compress local and remote image files. It is designed for developers using AI assistants that support MCP.
Install dependencies (pnpm i), build (pnpm build), then configure the mcp.json file with the command (bun or node), args pointing to the server entry, and the TINYPNG_API_KEY environment variable. Alternatively, install automatically via Smithery: npx -y @smithery/cli install @aiyogg/tinypng-mcp-server --client claude.
SUPPORTED_IMAGE_TYPES)The README does not explain how to obtain an API key; you must have one to set in the `TINYPNG_API_KEY` environment variable.
The server runs on Node.js or Bun. Both are supported via the `command` field in `mcp.json`.
Images are sent to the TinyPNG API for compression. The server itself does not store images; the compressed file is saved to the path you specify.
The server uses an enum called `SUPPORTED_IMAGE_TYPES`, but the exact list of formats is not provided in the README. Typical TinyPNG formats include PNG and JPEG.
No. A valid TinyPNG API key is required and must be provided in the environment configuration.

Model Context Protocol Servers
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
评论