{
  "markdown": "# GenAI Capture\n\n[![Downloads](https://img.shields.io/github/downloads/projecthsf/genai-capture/total?label=downloads)](https://github.com/projecthsf/genai-capture/releases)\n[![Latest release](https://img.shields.io/github/v/release/projecthsf/genai-capture?label=latest)](https://github.com/projecthsf/genai-capture/releases/latest)\n\nScreen capture + annotation, two ways:\n\n- **Desktop app** — capture the whole desktop, annotate (arrows, shapes, text,\n  highlighter, mosaic redaction, watermark), then copy / save / pin. Global\n  hotkeys, gallery, themes. Cross-platform (Java).\n- **JetBrains IDE plugin** (this repo's source) — the same engine inside any\n  JetBrains IDE: GoLand, PhpStorm, PyCharm, WebStorm, IntelliJ, CLion, Rider, …\n\n## Download the desktop app\n\nGrab the installer for your OS from **[Releases](https://github.com/projecthsf/genai-capture/releases)**:\n\n| OS | File |\n|---|---|\n| macOS | `GenAI Capture-<version>.dmg` |\n| Windows (installer) | `GenAI Capture-<version>.exe` |\n| Windows (portable) | `GenAI-Capture-portable-win.zip` |\n\n> **macOS note:** the app isn't notarized yet. If macOS blocks the first launch,\n> allow it under **System Settings ▸ Privacy & Security ▸ \"Open Anyway\"**, and grant\n> **Screen Recording** permission when asked. Details ship in the DMG's\n> *First Launch.txt*.\n\nThe plugin is on the [JetBrains Marketplace](https://plugins.jetbrains.com/) —\nsearch for **GenAI Capture** (or install the zip from Releases by hand).\n\n## Use with AI agents (MCP)\n\nThe desktop app (v1.2.0+) doubles as an **MCP server**: AI agents that speak the\n[Model Context Protocol](https://modelcontextprotocol.io) — Claude Code, Claude\nDesktop, Cursor, … — can capture your screen, **look at the image**, annotate it\n(arrows, boxes, text, highlight, blur/redact), and save the result. Visual bug\nreports and before/after proof, driven by one sentence to your AI.\n\nInstall the desktop app, then add the server to your client. Easiest (cross-platform,\nvia the [`genai-capture-mcp`](mcp-npm/) launcher on npm):\n\n```bash\nclaude mcp add genai-capture -- npx -y genai-capture-mcp\n```\n\nOr point directly at the installed binary (no Node needed):\n\n```bash\nclaude mcp add genai-capture -- \\\n  \"/Applications/GenAI Capture.app/Contents/MacOS/GenAI Capture\" --mcp\n```\n\nTools: `capture_fullscreen`, `capture_region`, `annotate`, `get_image`,\n`save_image`. Captures play an audible cue; everything runs locally — images\nonly go to the AI client you connected.\n\n---\n\n# JetBrains IDE plugin\n\nBrings the screenshot capture + annotation engine inside any JetBrains IDE\n(GoLand, PhpStorm, PyCharm, WebStorm, IntelliJ, CLion, Rider, …).\n\n## Features\n\n- **Tools ▸ Take Screenshot** — `⌘⇧1` (macOS) / `Ctrl+Shift+1` (Win/Linux).\n  Captures the whole desktop (IDE included) and opens the annotation overlay.\n- **Tools ▸ Capture Desktop (Hide IDE)** — `⌘⇧2` / `Ctrl+Shift+2`.\n  Temporarily hides the IDE, captures the desktop behind it, and keeps the IDE\n  hidden until you dismiss the overlay (ESC / save / copy / pin / close).\n- **Tools ▸ Take Delayed Screenshot ▸ 3s / 5s / 10s** — shows an on-screen\n  countdown, then captures (time to switch windows or open a menu first).\n- **Status-bar buttons** — a camera icon (immediate capture) and a monitor icon\n  (hide-IDE desktop capture). Toggle either via the status-bar right-click menu.\n- **Annotation overlay** — arrows, shapes, text, highlighter, mosaic redaction,\n  watermark, with copy / save / pin.\n- **Settings ▸ Tools ▸ GenAI Capture** — a **Watermark** page (appearance, default\n  text, behaviour, live preview) and a **Toolbar** page (choose/reorder the tools\n  on the capture toolbar). All shortcuts are rebindable in *Settings ▸ Keymap*.\n\nOn macOS, grant the IDE **Screen Recording** permission (System Settings ▸ Privacy\n& Security ▸ Screen Recording) or the capture comes back black — same requirement\nas any screen-capture tool.\n\n## How it's built\n\nIt **reuses the desktop app's code** (`../src/main/java` + `../src/main/resources`)\nvia a Gradle `Copy` step that filters out the app shell and the parts that don't\nload inside the IDE's JBR (the `osystem/` FFM code, jnativehook global-hotkey, tray,\nand the desktop-themed Settings panels). Thin FFM-free shims under\n`src/main/java/io/genai/screenshot/` (`osystem/AbstractOs`, `CaptureController`,\n`ScreenshotApp`) satisfy the few OS calls the overlay makes. The capture itself uses\n`java.awt.Robot` (no native code). The plugin's own actions, settings pages, and\nstatus-bar widgets live under `src/main/java/io/genai/screenshot/plugin/`.\n\nBuilt against the **platform module only** (`com.intellij.modules.platform`), so a\nsingle build runs in every JetBrains IDE.\n\n## Prerequisites\n\n- **JDK 17+** (a JBR or any JDK 17+).\n- A JetBrains IDE installed (the build targets your local **GoLand** by default —\n  see `build.gradle.kts`). To use a different IDE, edit the `local(\"…\")` line, or\n  switch to a downloaded one, e.g. `intellijIdeaCommunity(\"2024.1\")`.\n- Gradle: easiest is to **open this `jetbrains-plugin/` folder in IntelliJ IDEA**\n  (it imports the Gradle project and provides the wrapper). Or `brew install gradle`\n  and run `gradle wrapper` once.\n\n## Run it (sandbox IDE)\n\n```bash\ncd jetbrains-plugin\n./gradlew runIde          # launches GoLand with the plugin loaded\n```\n\nThen use **Tools ▸ Take Screenshot** (`⌘⇧1`) or the status-bar camera icon.\n\n## Build an installable plugin\n\n```bash\ncd jetbrains-plugin\n./gradlew buildPlugin      # -> build/distributions/genai-capture-plugin-1.0.0.zip\n```\n\nInstall in any IDE: **Settings ▸ Plugins ▸ ⚙ ▸ Install Plugin from Disk…** → pick the zip.\n\n## Notes / next steps\n\n- The reused overlay code is verified to compile at Java 17 with no FFM /\n  jnativehook dependency.\n- First `runIde` may need minor tweaks to the IntelliJ Platform Gradle DSL or the\n  `local(...)` IDE path for your exact versions — iterate from there.\n- Possible future options: capture a chosen region only, or a configurable\n  default delay.\n",
  "bytes": 5982,
  "sha": "0ca9093e06d0efe57db421172a461f4e478b4d6425add73435ce98de1210fe76",
  "repo_slug": "projecthsf/genai-capture",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_linhnnmt_genai_capture_bc6d962a/readme"
}