MCP server for Tinify image optimization — one tool, max optimization
https://app.tinify.ai/mcpnpx -y @tinify-ai/mcp-serverAdd this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
{
"mcpServers": {
"io-github-onepunchtechnology-tinify-ai": {
"command": "npx",
"args": [
"-y",
"@tinify-ai/mcp-server"
]
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonNo remote HTTP endpoint is advertised. Use the package or stdio setup shown in Install.
tinify-ai is an MCP server for MCP server for Tinify image optimization — one tool, max optimization. It supports STDIO, HTTP transport.
Use the generated config in Install. This server runs with npx -y @tinify-ai/mcp-server; add any required environment variables before starting your client.
Choose the Claude Desktop tab in Install, copy the config, and add it to Claude Desktop's MCP server settings. Endpoint: https://app.tinify.ai/mcp.
Choose the Claude Code tab in Install, copy the config, and add it to Claude Code's MCP server settings. Endpoint: https://app.tinify.ai/mcp.
Choose the Codex tab in Install, copy the config, and add it to Codex's MCP server settings. Endpoint: https://app.tinify.ai/mcp.
Choose the Cursor or VS Code tab in Install, copy the config, and add it to Cursor or VS Code's MCP server settings. Endpoint: https://app.tinify.ai/mcp.
tinify-ai uses STDIO, HTTP transport. Endpoint: https://app.tinify.ai/mcp.
tinify-ai inventory is listed when the MCP endpoint exposes tools, resources, or prompts. Some servers require auth first.
tinify-ai does not advertise a verified auth requirement. If discovery fails, it may still need provider login, an API key, a bearer token, or a session header.
| Package | Registry | Version | Inputs |
|---|---|---|---|
@tinify-ai/mcp-serverstdio | npm | 1.4.2 | None advertised |