Ui.Vision MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 703 installs a week from npm. Last commit 9 Aug 2026.
MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
Today is the operative word: we check Ui.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 uivision-mcp -- npx -y uivision-mcp-bridge
{
"mcpServers": {
"uivision-mcp": {
"args": [
"-y",
"uivision-mcp-bridge"
],
"command": "npx"
}
}
}
[mcp_servers.uivision-mcp]
command = "npx"
args = ["-y", "uivision-mcp-bridge"]
{
"mcpServers": {
"uivision-mcp": {
"args": [
"-y",
"uivision-mcp-bridge"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"uivision-mcp": {
"args": [
"-y",
"uivision-mcp-bridge"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
UIVISION_MCP_PORT (Local WebSocket port the Ui.Vision extension connects to (default 50888; must match Settings > AI in the extension)).
The author declared them in the registry entry; get the values from the project itself.
Desktop UI automation for AI agents: screenshots, windows, mouse, keyboard, UI Automation, OCR
MCP server for desktop, browser (CDP), and Android automation. Screenshot, OCR, click, type.
Windows desktop-control MCP server: screenshot, window mgmt, mouse/keyboard input, recording.
MCP server for AI web browser automation using Browserbase and Stagehand
Real signed-browser automation for AI agents, over a local stdio MCP server.
MCP server for browser automation via Vercel's agent-browser CLI
MCP server for browser automation with AI agent
Self-hosted MCP server for stealth browser automation with human-like OS-level input.
Answers built from our own checks of this server.