can-see
Let AI agents see and interact with terminal/CLI apps via PNG screenshots
Open the source (opens github.com) https://github.com/hurleysk/can-see
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.HurleySk.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
can-see@0.4.0
From the server's entry in the official MCP Registry
Settings it asks for
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)
Related
-
getsnap
MCP serversScreenshots, PDFs, visual diffs and accessibility audits, returned inline so a model can see them
getsnap-mcp@1.14.5 -
snaplab
MCP serversScreenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.
-
sticky
MCP serversPersistent memory and context for your agent, on a board you can see. Capped, so it stays small.
sticky-mcp@0.2.2 -
Nhost
MCP serversLet your users work with their own data through an AI assistant, limited to what they can see.
docker.io/nhost/mcp:0.4.0-beta2 -
snaplab
MCP serversScreenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.
-
dittu
MCP serversTurns a phone into a camera+Bluetooth remote so AI assistants can see and control any PC.