Macos Vision MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 111 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": {
"args": [
"-y",
"macos-vision-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.macos-vision-mcp]
command = "npx"
args = ["-y", "macos-vision-mcp"]
{
"mcpServers": {
"macos-vision-mcp": {
"args": [
"-y",
"macos-vision-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"macos-vision-mcp": {
"args": [
"-y",
"macos-vision-mcp"
],
"command": "npx"
}
}
}
Capture, OCR-search, and retrieve local Mac screenshots for AI agents through Stashot.
Safety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control.
Local file tools for agents: documents, PDFs, images, QR codes. Nothing is uploaded.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Local, private PDF to Markdown for agents: geometry-first parsing, OCR only where needed.
Invoices and other financial documents to rows: upload, say what to extract, read the rows.
Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.
Read local PDFs without uploading. Classifies first, flags untrustworthy text, bounds output.
Answers built from our own checks of this server.