Server data from the Official MCP Registry
Let AI agents see and interact with terminal/CLI apps via PNG screenshots
Let AI agents see and interact with terminal/CLI apps via PNG screenshots
Valid MCP server (3 strong, 4 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.
5 files analyzed · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: DEFAULT_COLS
Environment variable: DEFAULT_ROWS
Environment variable: IDLE_TIMEOUT_MS
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-hurleysk-can-see": {
"env": {
"DEFAULT_COLS": "your-default-cols-here",
"DEFAULT_ROWS": "your-default-rows-here",
"IDLE_TIMEOUT_MS": "your-idle-timeout-ms-here"
},
"args": [
"-y",
"can-see"
],
"command": "npx"
}
}
}From the project's GitHub README.
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.
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.
npm install -g can-see
can-see depends on node-canvas (Cairo) and node-pty, which require native compilation. Most systems will need:
npm install --global windows-build-tools or install from Visual Studio Installerxcode-select --installsudo apt install build-essential libcairo2-dev libjpeg-dev libpango1.0-dev libgif-dev librsvg2-devAdd 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"
}
}
}
can-see uses stdio transport. Point your MCP client at the can-see binary or npx -y can-see.
| 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, Ctrl+C, ['Down', 'Down', 'Enter']). |
send_text | Type a string of text into the app. |
get_process_status | Get process status — distinguish "app is idle" from "app has exited". Returns PID, running state, exit code. |
list_sessions | List all active terminal sessions. |
close | Kill the app and clean up. Always close when done. |
close_all | Kill all active sessions at once. Useful for cleanup between test runs. |
Enter, Tab, Escape, Backspace, Space, Up, Down, Left, Right, Home, End, Delete, PageUp, PageDown, Ctrl+A through Ctrl+Z.
| 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) |
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")
New tools:
wait_for_exit — wait for process exit, get exit code and signalclose_all — kill all active sessions at onceget_process_status — distinguish "app is idle" from "app has exited"screenshot_text_region — find text in viewport, capture surrounding area as PNGEnhancements:
launch accepts env parameter for custom environment variableswait_for_idle supports excludePattern (regex) for dynamic row exclusion in stableMs modestop_recording returns frameCount and durationMs metadata alongside GIFget_cell_info supports compact option for reduced output ({char, fg, bold} only)Bug fixes:
wait_for_text and wait_for_color race condition where text/color present in the final buffer was missed when the process exited simultaneouslystableMs and idleMs are passed to wait_for_idleMIT
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.