Offline OCR and image analysis with Apple's Vision framework: text from images and PDFs, face, barcode and QR detection, and classification.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add macos-vision -- npx -y macos-vision-mcp~/.codex/config.toml
[mcp_servers.macos-vision]
command = "npx"
args = ["-y", "macos-vision-mcp"]
# codex mcp add macos-vision -- npx -y macos-vision-mcp~/.cursor/mcp.json
{
"mcpServers": {
"macos-vision": {
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"macos-vision": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"macos-vision": {
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"macos-vision": {
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"macos-vision": {
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}