How do I install Can See?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Can See need an API key?

The publisher lists these environment variables: DEFAULT_COLS, DEFAULT_ROWS, IDLE_TIMEOUT_MS.

What transport does Can See use?

Can See runs locally over stdio.

When was Can See last checked?

Last checked 2026-11-09. Let AI agents see and interact with terminal/CLI apps via PNG screenshots

Can See MCP server

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y [email protected]

Credentials from the publisher

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)

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1DEFAULT_COLS=<value> DEFAULT_ROWS=<value> IDLE_TIMEOUT_MS=<value> claude mcp add io.github.hurleysk-can-see -- npx -y can-see@0.4.0

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "io.github.hurleysk-can-see": {4      "command": "npx",5      "args": [6        "-y",7        "[email protected]"8      ],9      "env": {10        "DEFAULT_COLS": "<value>",11        "DEFAULT_ROWS": "<value>",12        "IDLE_TIMEOUT_MS": "<value>"13      }14    }15  }16}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 0.4.0
API key

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

can-see

MCP server that lets AI agents see and interact with terminal/CLI applications through virtual terminals and PNG screenshots.

Built for Claude Code and any MCP-compatible agent.

Why?

Some things are easier to show than describe. When debugging a TUI app, an interactive CLI wizard, or anything with visual terminal output, can-see lets the agent see exactly what you see — colors, layout, cursor position, and all.

How it works

Launch a CLI app in a virtual terminal (node-pty + @xterm/headless)
Screenshot the terminal as a PNG image (rendered via node-canvas)
Send keys/text to interact with the app
Screenshot again to see the result
Close the session when done

Installation

npm install -g can-see

Prerequisites

can-see depends on node-canvas (Cairo) and node-pty, which require native compilation. Most systems will need:

Windows: Visual Studio Build Tools (C++ workload) — npm install --global windows-build-tools or install from Visual Studio Installer
macOS: Xcode Command Line Tools — xcode-select --install
Linux: sudo apt install build-essential libcairo2-dev libjpeg-dev libpango1.0-dev libgif-dev librsvg2-dev

Configuration

Claude Code

Add to your project's .mcp.json:

{
  "mcpServers": {
    "can-see": {
      "command": "npx",
      "args": ["-y", "can-see"]
    }
  }
}

Or if installed globally:

{
  "mcpServers": {
    "can-see": {
      "command": "can-see"
    }
  }
}

Other MCP clients

can-see uses stdio transport. Point your MCP client at the can-see binary or npx -y can-see.

Tools

Tool	Description
`launch`	Start a CLI app in a virtual terminal. Returns a `sessionId`. Accepts optional `env` to set environment variables.
`screenshot`	Capture the terminal as a PNG image.
`screenshot_region`	Capture a specific rectangular area of the terminal.
`screenshot_text_region`	Find text in the viewport and capture the surrounding area as a PNG.
`capture_baseline`	Snapshot terminal state for later diff comparison.
`diff_screenshot`	Compare current state against baseline with highlighted changes.
`get_cell_info`	Query character, colors, and attributes at specific cell(s). Supports `compact` mode for reduced output.
`read_text`	Read the terminal buffer as plain text.
`read_scrollback`	Read text that scrolled above the visible viewport.
`wait_for_text`	Wait until specific text appears in the terminal buffer.
`wait_for_idle`	Wait until terminal output has been stable for a given duration. Supports `stableMs` for content-comparison mode (for apps with timers/spinners), `excludeRows` to ignore specific rows, and `excludePattern` (regex) for dynamic row exclusion.
`wait_for_color`	Wait until a specific color appears at a position.
`wait_for_exit`	Wait until the process exits and return its exit code and signal.
`start_recording`	Begin capturing frames for an animated GIF.
`stop_recording`	Stop recording and return the animated GIF with metadata (`frameCount`, `durationMs`). Auto-trims frames or saves to file if GIF exceeds inline size limit.
`send_keys`	Send keystrokes (e.g., `Enter`, , ).

Supported keys

Enter, Tab, Escape, Backspace, Space, Up, Down, Left, Right, Home, End, Delete, PageUp, PageDown, Ctrl+A through Ctrl+Z.

Environment variables

Variable	Default	Description
`DEFAULT_COLS`	`120`	Terminal width in columns
`DEFAULT_ROWS`	`30`	Terminal height in rows
`IDLE_TIMEOUT_MS`	`300000`	Auto-close idle sessions after this many ms (5 min)

Example usage

From an MCP-connected agent:

Agent: I'll launch your app to see what's happening.
→ launch("node", ["app.js"])  → sessionId: "abc-123"

Agent: Let me wait for the app to start.
→ wait_for_text("abc-123", "Ready")  → Found "Ready" after 1200ms

Agent: Let me read the current output.
→ read_text("abc-123")  → "Welcome to MyApp\nReady\n> "

Agent: I can see the prompt. Let me select option 2.
→ send_keys("abc-123", ["Down", "Enter"])

Agent: Waiting for the screen to settle.
→ wait_for_idle("abc-123")  → Terminal idle for 520ms

Agent: Let me check the result.
→ screenshot("abc-123")  → [PNG image showing result]

Agent: Done, closing the session.
→ close("abc-123")

Changelog

0.5.0

New tools:

wait_for_exit — wait for process exit, get exit code and signal
close_all — kill all active sessions at once
get_process_status — distinguish "app is idle" from "app has exited"
screenshot_text_region — find text in viewport, capture surrounding area as PNG

Enhancements:

launch accepts env parameter for custom environment variables
wait_for_idle supports excludePattern (regex) for dynamic row exclusion in stableMs mode
stop_recording returns frameCount and durationMs metadata alongside GIF
get_cell_info supports compact option for reduced output ({char, fg, bold} only)

Bug fixes:

Fixed wait_for_text and wait_for_color race condition where text/color present in the final buffer was missed when the process exited simultaneously
Added mutual exclusion validation when both stableMs and idleMs are passed to wait_for_idle

License

MIT

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install Can See?

Does Can See need an API key?

What transport does Can See use?

When was Can See last checked?

Documentation

can-see

Why?

How it works

Installation

Prerequisites

Configuration

Claude Code

Other MCP clients

Tools

Supported keys

Environment variables

Example usage

Changelog

0.5.0

License