From 925bc08481c474ce4c98c62045a026905fc4340e Mon Sep 17 00:00:00 2001
From: ostapondo <33957189+ostapondo@users.noreply.github.com>
Date: Mon, 10 Aug 2026 12:32:03 +0200
Subject: [PATCH 1/5] Add ostapondo/plonk to OS Automation
---
README.md | 1 +
1 file changed, 1 insertion(+)
diff --git a/README.md b/README.md
index 67370cd77..b6ff77220 100644
--- a/README.md
+++ b/README.md
@@ -2784,6 +2784,7 @@ Servers for controlling the desktop operating system: screenshots, window manage
- [juergenkoller-software/freezetext-mcp](https://github.com/juergenkoller-software/freezetext-mcp) [](https://glama.ai/mcp/servers/juergenkoller-software/freezetext-mcp) 🏠 🍎 - MCP server for [FreezeText](https://store.juergenkoller.software/en/apps/freezetext) — OCR anything on your Mac screen. Freeze the screen and extract text via Apple Vision (videos, popups, protected PDFs), OCR a region or base64 image, and manage a searchable capture history. 12 tools.
- [faze79/WPFVisualTreeMcp](https://github.com/faze79/WPFVisualTreeMcp) [](https://glama.ai/mcp/servers/faze79/WPFVisualTreeMcp) #️⃣ 🏠 🪟 - Inspect, debug and drive running WPF (.NET desktop) apps: visual tree, dependency properties, data bindings and binding errors, DataContext, and screenshots with open popups/menus included, plus clicking, item selection, text input and keyboard shortcuts. Auto-injects into any running WPF process (x64/x86) with no source changes. `dotnet tool install -g WpfVisualTreeMcp`
- [fixed-width/glass](https://github.com/fixed-width/glass) [](https://glama.ai/mcp/servers/fixed-width/glass) 🦀 🏠 🍎 🪟 🐧 - Gives a coding agent a build → see → interact → debug loop over the native GUI app it is writing: launch the app, screenshot it, read its accessibility tree, inject mouse/keyboard/gestures, tail its logs, and diff frames to confirm a change landed. Drives apps as an external black box with no app integration, so any toolkit or language works. 30 tools with text-first responses (element ids, diffs, waits) so the agent need not screenshot every step, plus optional sandboxing of the launched app. Backends: X11, Wayland, Windows, macOS, Android emulators, and the iOS Simulator.
+- [ostapondo/plonk](https://github.com/ostapondo/plonk) 📇 🏠 🍎 - Mac window manager agents can drive: see every monitor and window, arrange layouts across displays in one call, save workspaces that relaunch apps into their places, snap zones, keep-awake, and annotated screenshots. Backed by a native menu bar app over a local-only loopback API. `npx -y plonk-mcp`
### 🎙️ Podcasts
From 8a5d533e0b704c870243589feba026a1440093ca Mon Sep 17 00:00:00 2001
From: ostapondo <33957189+ostapondo@users.noreply.github.com>
Date: Mon, 10 Aug 2026 12:32:03 +0200
Subject: [PATCH 2/5] Add Glama score badge to plonk entry
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index b6ff77220..c41ed2117 100644
--- a/README.md
+++ b/README.md
@@ -2784,7 +2784,7 @@ Servers for controlling the desktop operating system: screenshots, window manage
- [juergenkoller-software/freezetext-mcp](https://github.com/juergenkoller-software/freezetext-mcp) [](https://glama.ai/mcp/servers/juergenkoller-software/freezetext-mcp) 🏠 🍎 - MCP server for [FreezeText](https://store.juergenkoller.software/en/apps/freezetext) — OCR anything on your Mac screen. Freeze the screen and extract text via Apple Vision (videos, popups, protected PDFs), OCR a region or base64 image, and manage a searchable capture history. 12 tools.
- [faze79/WPFVisualTreeMcp](https://github.com/faze79/WPFVisualTreeMcp) [](https://glama.ai/mcp/servers/faze79/WPFVisualTreeMcp) #️⃣ 🏠 🪟 - Inspect, debug and drive running WPF (.NET desktop) apps: visual tree, dependency properties, data bindings and binding errors, DataContext, and screenshots with open popups/menus included, plus clicking, item selection, text input and keyboard shortcuts. Auto-injects into any running WPF process (x64/x86) with no source changes. `dotnet tool install -g WpfVisualTreeMcp`
- [fixed-width/glass](https://github.com/fixed-width/glass) [](https://glama.ai/mcp/servers/fixed-width/glass) 🦀 🏠 🍎 🪟 🐧 - Gives a coding agent a build → see → interact → debug loop over the native GUI app it is writing: launch the app, screenshot it, read its accessibility tree, inject mouse/keyboard/gestures, tail its logs, and diff frames to confirm a change landed. Drives apps as an external black box with no app integration, so any toolkit or language works. 30 tools with text-first responses (element ids, diffs, waits) so the agent need not screenshot every step, plus optional sandboxing of the launched app. Backends: X11, Wayland, Windows, macOS, Android emulators, and the iOS Simulator.
-- [ostapondo/plonk](https://github.com/ostapondo/plonk) 📇 🏠 🍎 - Mac window manager agents can drive: see every monitor and window, arrange layouts across displays in one call, save workspaces that relaunch apps into their places, snap zones, keep-awake, and annotated screenshots. Backed by a native menu bar app over a local-only loopback API. `npx -y plonk-mcp`
+- [ostapondo/plonk](https://github.com/ostapondo/plonk) [](https://glama.ai/mcp/servers/ostapondo/plonk) 📇 🏠 🍎 - Mac window manager agents can drive: see every monitor and window, arrange layouts across displays in one call, save workspaces that relaunch apps into their places, snap zones, keep-awake, and annotated screenshots. Backed by a native menu bar app over a local-only loopback API. `npx -y plonk-mcp`
### 🎙️ Podcasts
From 76cbd80ef097c7c2e1bf811fa7460d7ab3b1e60a Mon Sep 17 00:00:00 2001
From: ostapondo <33957189+ostapondo@users.noreply.github.com>
Date: Mon, 10 Aug 2026 12:32:03 +0200
Subject: [PATCH 3/5] Plonk: name the OCR tool, and lead with what the server
actually covers
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index c41ed2117..482e0bbd4 100644
--- a/README.md
+++ b/README.md
@@ -2784,7 +2784,7 @@ Servers for controlling the desktop operating system: screenshots, window manage
- [juergenkoller-software/freezetext-mcp](https://github.com/juergenkoller-software/freezetext-mcp) [](https://glama.ai/mcp/servers/juergenkoller-software/freezetext-mcp) 🏠 🍎 - MCP server for [FreezeText](https://store.juergenkoller.software/en/apps/freezetext) — OCR anything on your Mac screen. Freeze the screen and extract text via Apple Vision (videos, popups, protected PDFs), OCR a region or base64 image, and manage a searchable capture history. 12 tools.
- [faze79/WPFVisualTreeMcp](https://github.com/faze79/WPFVisualTreeMcp) [](https://glama.ai/mcp/servers/faze79/WPFVisualTreeMcp) #️⃣ 🏠 🪟 - Inspect, debug and drive running WPF (.NET desktop) apps: visual tree, dependency properties, data bindings and binding errors, DataContext, and screenshots with open popups/menus included, plus clicking, item selection, text input and keyboard shortcuts. Auto-injects into any running WPF process (x64/x86) with no source changes. `dotnet tool install -g WpfVisualTreeMcp`
- [fixed-width/glass](https://github.com/fixed-width/glass) [](https://glama.ai/mcp/servers/fixed-width/glass) 🦀 🏠 🍎 🪟 🐧 - Gives a coding agent a build → see → interact → debug loop over the native GUI app it is writing: launch the app, screenshot it, read its accessibility tree, inject mouse/keyboard/gestures, tail its logs, and diff frames to confirm a change landed. Drives apps as an external black box with no app integration, so any toolkit or language works. 30 tools with text-first responses (element ids, diffs, waits) so the agent need not screenshot every step, plus optional sandboxing of the launched app. Backends: X11, Wayland, Windows, macOS, Android emulators, and the iOS Simulator.
-- [ostapondo/plonk](https://github.com/ostapondo/plonk) [](https://glama.ai/mcp/servers/ostapondo/plonk) 📇 🏠 🍎 - Mac window manager agents can drive: see every monitor and window, arrange layouts across displays in one call, save workspaces that relaunch apps into their places, snap zones, keep-awake, and annotated screenshots. Backed by a native menu bar app over a local-only loopback API. `npx -y plonk-mcp`
+- [ostapondo/plonk](https://github.com/ostapondo/plonk) [](https://glama.ai/mcp/servers/ostapondo/plonk) 📇 🏠 🍎 - Ten Mac menu bar utilities agents can drive: see every monitor and window, arrange layouts across displays in one call, save workspaces that relaunch apps into their places, snap zones, keep-awake, annotated screenshots, and text read off the screen on-device, handed back a box per line so what was read can be pointed at. Backed by a native menu bar app over a local-only loopback API. `npx -y plonk-mcp`
### 🎙️ Podcasts
From 82672360458ef3e6ec8a47ebd95fd7f892a98781 Mon Sep 17 00:00:00 2001
From: ostapondo <33957189+ostapondo@users.noreply.github.com>
Date: Mon, 10 Aug 2026 13:08:27 +0200
Subject: [PATCH 4/5] Plonk: cover what 0.2.4 added, and how Claude Desktop
installs it
The entry was written against 0.1.0. Since then the server can photograph
a window by name without raising it, and every release ships an .mcpb
bundle, which is the shorter of the two install paths for Claude Desktop.
Co-Authored-By: Claude Opus 5 (1M context)
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index 482e0bbd4..e28d6e72b 100644
--- a/README.md
+++ b/README.md
@@ -2784,7 +2784,7 @@ Servers for controlling the desktop operating system: screenshots, window manage
- [juergenkoller-software/freezetext-mcp](https://github.com/juergenkoller-software/freezetext-mcp) [](https://glama.ai/mcp/servers/juergenkoller-software/freezetext-mcp) 🏠 🍎 - MCP server for [FreezeText](https://store.juergenkoller.software/en/apps/freezetext) — OCR anything on your Mac screen. Freeze the screen and extract text via Apple Vision (videos, popups, protected PDFs), OCR a region or base64 image, and manage a searchable capture history. 12 tools.
- [faze79/WPFVisualTreeMcp](https://github.com/faze79/WPFVisualTreeMcp) [](https://glama.ai/mcp/servers/faze79/WPFVisualTreeMcp) #️⃣ 🏠 🪟 - Inspect, debug and drive running WPF (.NET desktop) apps: visual tree, dependency properties, data bindings and binding errors, DataContext, and screenshots with open popups/menus included, plus clicking, item selection, text input and keyboard shortcuts. Auto-injects into any running WPF process (x64/x86) with no source changes. `dotnet tool install -g WpfVisualTreeMcp`
- [fixed-width/glass](https://github.com/fixed-width/glass) [](https://glama.ai/mcp/servers/fixed-width/glass) 🦀 🏠 🍎 🪟 🐧 - Gives a coding agent a build → see → interact → debug loop over the native GUI app it is writing: launch the app, screenshot it, read its accessibility tree, inject mouse/keyboard/gestures, tail its logs, and diff frames to confirm a change landed. Drives apps as an external black box with no app integration, so any toolkit or language works. 30 tools with text-first responses (element ids, diffs, waits) so the agent need not screenshot every step, plus optional sandboxing of the launched app. Backends: X11, Wayland, Windows, macOS, Android emulators, and the iOS Simulator.
-- [ostapondo/plonk](https://github.com/ostapondo/plonk) [](https://glama.ai/mcp/servers/ostapondo/plonk) 📇 🏠 🍎 - Ten Mac menu bar utilities agents can drive: see every monitor and window, arrange layouts across displays in one call, save workspaces that relaunch apps into their places, snap zones, keep-awake, annotated screenshots, and text read off the screen on-device, handed back a box per line so what was read can be pointed at. Backed by a native menu bar app over a local-only loopback API. `npx -y plonk-mcp`
+- [ostapondo/plonk](https://github.com/ostapondo/plonk) [](https://glama.ai/mcp/servers/ostapondo/plonk) 📇 🏠 🍎 - Ten Mac menu bar utilities an agent can drive: see every monitor and window, arrange a layout across displays in one call, save workspaces that relaunch apps into their places, snap zones you drew yourself, keep-awake, screenshot a window by name even when it is buried behind other windows, annotate it, and read text off the screen on-device — handed back a box per line, so what was read can be pointed at. Backed by a native menu bar app over a local-only loopback API; no cloud, no telemetry. `npx -y plonk-mcp`, or open the shipped `.mcpb` bundle in Claude Desktop.
### 🎙️ Podcasts
From 67996292a2982c009a37d432de2a50222209a787 Mon Sep 17 00:00:00 2001
From: ostapondo <33957189+ostapondo@users.noreply.github.com>
Date: Sun, 16 Aug 2026 01:46:00 +0200
Subject: [PATCH 5/5] Plonk: lead with the window manager, and name the tool
count
Match how the project now describes itself: the window manager first,
the other ten utilities after it. Adds the 20-tool count, and uses the
repository's own capitalisation so the links and the Glama badge
resolve without a redirect.
Co-Authored-By: Claude Opus 5 (1M context)
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index e28d6e72b..aaa598336 100644
--- a/README.md
+++ b/README.md
@@ -2784,7 +2784,7 @@ Servers for controlling the desktop operating system: screenshots, window manage
- [juergenkoller-software/freezetext-mcp](https://github.com/juergenkoller-software/freezetext-mcp) [](https://glama.ai/mcp/servers/juergenkoller-software/freezetext-mcp) 🏠 🍎 - MCP server for [FreezeText](https://store.juergenkoller.software/en/apps/freezetext) — OCR anything on your Mac screen. Freeze the screen and extract text via Apple Vision (videos, popups, protected PDFs), OCR a region or base64 image, and manage a searchable capture history. 12 tools.
- [faze79/WPFVisualTreeMcp](https://github.com/faze79/WPFVisualTreeMcp) [](https://glama.ai/mcp/servers/faze79/WPFVisualTreeMcp) #️⃣ 🏠 🪟 - Inspect, debug and drive running WPF (.NET desktop) apps: visual tree, dependency properties, data bindings and binding errors, DataContext, and screenshots with open popups/menus included, plus clicking, item selection, text input and keyboard shortcuts. Auto-injects into any running WPF process (x64/x86) with no source changes. `dotnet tool install -g WpfVisualTreeMcp`
- [fixed-width/glass](https://github.com/fixed-width/glass) [](https://glama.ai/mcp/servers/fixed-width/glass) 🦀 🏠 🍎 🪟 🐧 - Gives a coding agent a build → see → interact → debug loop over the native GUI app it is writing: launch the app, screenshot it, read its accessibility tree, inject mouse/keyboard/gestures, tail its logs, and diff frames to confirm a change landed. Drives apps as an external black box with no app integration, so any toolkit or language works. 30 tools with text-first responses (element ids, diffs, waits) so the agent need not screenshot every step, plus optional sandboxing of the launched app. Backends: X11, Wayland, Windows, macOS, Android emulators, and the iOS Simulator.
-- [ostapondo/plonk](https://github.com/ostapondo/plonk) [](https://glama.ai/mcp/servers/ostapondo/plonk) 📇 🏠 🍎 - Ten Mac menu bar utilities an agent can drive: see every monitor and window, arrange a layout across displays in one call, save workspaces that relaunch apps into their places, snap zones you drew yourself, keep-awake, screenshot a window by name even when it is buried behind other windows, annotate it, and read text off the screen on-device — handed back a box per line, so what was read can be pointed at. Backed by a native menu bar app over a local-only loopback API; no cloud, no telemetry. `npx -y plonk-mcp`, or open the shipped `.mcpb` bundle in Claude Desktop.
+- [ostapondo/Plonk](https://github.com/ostapondo/Plonk) [](https://glama.ai/mcp/servers/ostapondo/Plonk) 📇 🏠 🍎 - A Mac window manager an agent can drive, plus ten more menu bar utilities behind the same icon: see every monitor and window, arrange a layout across displays in one call, snap a window into zones you drew yourself, save workspaces that relaunch apps into their places, keep-awake, measure the screen, screenshot a window by name even when it is buried behind other windows, annotate it, and read text off the screen on-device — handed back a box per line, so what was read can be pointed at. 20 tools, backed by a native menu bar app over a local-only loopback API; no cloud, no telemetry. `npx -y plonk-mcp`, or open the shipped `.mcpb` bundle in Claude Desktop.
### 🎙️ Podcasts