Can See runs on your own machine — the client starts it, so there is no endpoint to ping. 114 installs a week from npm. Last commit 22 May 2026.
Let AI agents see and interact with terminal/CLI apps via PNG screenshots
Today is the operative word: we check Can See 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 can-see -- npx -y can-see
{
"mcpServers": {
"can-see": {
"args": [
"-y",
"can-see"
],
"command": "npx"
}
}
}
[mcp_servers.can-see]
command = "npx"
args = ["-y", "can-see"]
{
"mcpServers": {
"can-see": {
"args": [
"-y",
"can-see"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"can-see": {
"args": [
"-y",
"can-see"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
DEFAULT_COLS (Terminal width in columns (default: 120)), DEFAULT_ROWS (Terminal height in rows (default: 30)), IDLE_TIMEOUT_MS (Auto-close idle sessions after this many milliseconds (default: 300000)).
The author declared them in the registry entry; get the values from the project itself.
Let AI agents inspect and drive running WPF apps: tree, bindings, screenshots, clicks, text input.
Create App Store and Play Store screenshots with AI via MCP
MCP server for AI agents to interact with terminal applications. Think Playwright for terminals.
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
The terminal AI agents can drive: spawn panes, run commands, read screens, scrolling screenshots.
Generate PDFs, screenshots, and documents via any MCP-compatible AI agent.
Deterministic UI extraction and screenshot diffing for AI coding agents.
Answers built from our own checks of this server.