Macos Vision MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 97 installs a week from npm. Last commit 25 Aug 2026.
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
Today is the operative word: we check Macos Vision MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add macos-vision-mcp -- npx -y macos-vision-mcp
{
"mcpServers": {
"macos-vision-mcp": {
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}
[mcp_servers.macos-vision-mcp]
command = "npx"
args = ["-y", "macos-vision-mcp"]
{
"mcpServers": {
"macos-vision-mcp": {
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}
{
"servers": {
"macos-vision-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"macos-vision-mcp"
]
}
}
}
Plonk gives agents local macOS tools for windows, workspaces, screenshots, OCR, and more.
Capture, OCR-search, and retrieve local Mac screenshots for AI agents through Stashot.
Windows screenshots, OCR, and redacted screen recording for AI agents. No desktop app needed.
Safety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control.
Web search, page reading, HTML to PDF, file upload and flight search for AI agents, paid in USDC.
Local file tools for agents: documents, PDFs, images, QR codes. Nothing is uploaded.
Turn bug screen recordings into chronological context for AI agents: frames, OCR, logcat, voice.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Answers built from our own checks of this server.