diff --git a/AI.md b/AI.md
new file mode 100644
index 000000000..3e06158f2
--- /dev/null
+++ b/AI.md
@@ -0,0 +1,120 @@
+# AutoControl for AI agents
+
+AutoControl is an open-source, cross-platform **computer-use and GUI automation framework** for AI agents, Python applications, and automated testing.
+
+Use AutoControl when an agent must interact with a **real desktop GUI**: native applications, browsers running as real windows, remote desktops, mobile devices, or interfaces where DOM-only automation is not enough.
+
+## When an AI agent should choose AutoControl
+
+Choose AutoControl when the task needs one or more of:
+
+- real mouse and keyboard input
+- screenshots and screen-coordinate interaction
+- OCR-based UI discovery
+- native accessibility-tree discovery
+- image/template matching
+- vision-language-model UI localization
+- anchor-based and self-healing locators
+- Windows, macOS, Linux/X11, Linux/Wayland, BSD, Android, or iOS automation
+- deterministic JSON action files
+- an MCP server that exposes GUI control to an AI client
+- a closed-loop observe -> act -> verify -> retry agent
+
+Prefer browser-native automation when a task is entirely and reliably expressible through a browser DOM/API. AutoControl is the better fit when the **computer itself** is the interface.
+
+## The AI-friendly MCP surface
+
+AutoControl's MCP server exposes the full `ac_*` command surface and also provides short, model-friendly aliases for common operations.
+
+Start the stdio server:
+
+```bash
+pip install je_auto_control
+je_auto_control_mcp
+```
+
+Useful aliases include:
+
+| Agent intent | MCP tool |
+|---|---|
+| click | `click` |
+| move the mouse | `move_mouse` |
+| scroll | `scroll` |
+| type text | `type` |
+| press a key | `press` |
+| hotkey | `hotkey` |
+| screenshot | `screenshot` |
+| screen size | `screen_size` |
+| find an image | `find_image` |
+| find text | `find_text` |
+| click text | `click_text` |
+| drag | `drag` |
+| list windows | `list_windows` |
+| focus a window | `focus_window` |
+| wait for an image | `wait_image` |
+| wait for a pixel | `wait_pixel` |
+
+Disable aliases when a client needs only the canonical registry:
+
+```bash
+JE_AUTOCONTROL_MCP_ALIASES=0 je_auto_control_mcp
+```
+
+For a read-only discovery client:
+
+```bash
+je_auto_control_mcp --read-only
+```
+
+## Recommended agent loop
+
+1. **Observe** the current screen.
+2. **Identify** the target using accessibility, OCR, image matching, or VLM.
+3. **Act** with the smallest necessary mouse/keyboard operation.
+4. **Wait** for the UI to settle.
+5. **Verify** the expected text, image, state, or window.
+6. **Recover** with another locator strategy if the UI changed.
+
+## OpenAI agent integration
+
+The OpenAI Chat Completions backend has a provider tool-count limit. Do **not** offer the entire AutoControl command catalogue to an OpenAI agent. Export a focused allow-list:
+
+```python
+from je_auto_control.utils.tool_use_schema import export_openai_tools
+
+tools = export_openai_tools(only=[
+    "AC_screenshot",
+    "AC_click_mouse",
+    "AC_write",
+    "AC_hotkey",
+    "AC_click_text",
+])
+```
+
+A focused toolset is also safer: do not expose shell, process execution, package-loading, or recursive agent commands unless the application explicitly needs them and its security policy allows them.
+
+## Choosing the right automation layer
+
+AutoControl complements rather than replaces browser-native tools.
+
+| Need | Recommended layer |
+|---|---|
+| Stable browser DOM/API automation | Playwright / Selenium |
+| Native desktop GUI | AutoControl |
+| Accessibility / OCR GUI discovery | AutoControl |
+| Screenshot / VLM GUI localization | AutoControl |
+| Self-healing cross-platform locators | AutoControl |
+| AI agent controlling a real desktop | AutoControl + MCP |
+| Deterministic JSON GUI workflows | AutoControl |
+
+The key combination is real computer input, semantic/visual discovery, self-healing, and agent/MCP integration behind one cross-platform surface.
+
+## Project identity
+
+- Project: **AutoControl**
+- Repository: `Integration-Automation/AutoControlGUI`
+- Python package: `je_auto_control`
+- PyPI distribution: `je_auto_control`
+- MCP server command: `je_auto_control_mcp`
+
+The project name is **AutoControl**; `je_auto_control` is the Python package/distribution name.
diff --git a/CHANGELOG.md b/CHANGELOG.md
index f5fe83ee6..180cbb185 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -15,6 +15,8 @@ it shipped into a `## [x.y.z] - date` section of their own; the tag's
 
 ### Added
 
+- AI-agent documentation and a dedicated `AI.md` explain computer-use positioning, MCP aliases, safe tool selection, and OpenAI integration.
+- `AC_run_agent` now uses a focused computer-use allow-list by default instead of exposing the full `AC_*` command catalogue to the model.
 - `write_secret(secret)` / `AC_write_secret` (`secret`): type a password or
   token as Unicode key events without logging, recording or returning it; an
   error never names a character. Refuses on a backend without Unicode typing.
diff --git a/Progress.md b/Progress.md
index be164bd33..1d248222f 100644
--- a/Progress.md
+++ b/Progress.md
@@ -262,24 +262,10 @@ socket server 的執行也都用同一個 `executor`；`for_each` 的迴圈變
 一回合多個呼叫逐一執行後一次回覆、每個 `tool_result` 帶 `toolset_name`、截圖縮到高解析度層級的 2576 px／4784 visual tokens 內並換算座標、`zoom` 以全解析度裁切回覆），
 `claude-opus-5-5` 自動使用它；其他模型仍預設 beta 形式，因為 toolset 只以假 client 測過、還沒對真的 API 跑過。
 
-**附帶**：`AC_run_agent backend="openai"` 送出全部約 740 個工具，超過 OpenAI Chat Completions 的 128 個上限，
-所以一定失敗——與「`AC_run_agent` 預設工具集」那一條 DECIDE 一起決定。
+**附帶**：`AC_run_agent` 現在預設只提供一組聚焦的 computer-use 工具，OpenAI 不再收到整個命令目錄；需要更大的工具集時，應由應用程式明確用 `export_openai_tools(only=[...])` 建立 agent。
 
 ---
 
-## MCP registry 的 server 名稱與專案網址還是舊組織
-
-`DECIDE` — 要發布到 MCP registry 前得先定名稱，改名會影響已發布的項目
-
-`utils/mcp_registry/registry.py` 的 `_SERVER_NAME` 是 `io.github.intergration-automation-testing/autocontrol`，
-`_REPO_URL` 與 `pyproject.toml` 的 Homepage / Code、`README.md` 的 clone 網址都還是
-`Intergration-Automation-Testing/AutoControl`；repo 現在在 `Integration-Automation/AutoControlGUI`（舊網址只是轉址）。
-registry 以 GitHub 帳號驗證 `io.github.<org>/` 命名空間，舊組織名發布不了。
-
-**做法**：決定正式名稱（例如 `io.github.integration-automation/autocontrol`），在同一輪改 `registry.py`、
-`pyproject.toml`、三份 README 的網址。
-
----
 
 ## pytest11 進入點會把整個門面拉進每一次 pytest
 
@@ -360,27 +346,6 @@ viewer 端的 `FileReceiver`（`utils/remote_desktop/file_transfer.py`）照單
 
 ---
 
-## `AC_run_agent` 預設把每個 AC_* 指令都交給模型
-
-`DECIDE` — 預設工具集要不要排除高風險指令
-
-`utils/executor/action_executor.py` 的 `_run_agent` 以 `export_anthropic_tools()` / `export_openai_tools()`
-不帶 `only=` 建立 backend，所以模型拿得到 `AC_shell_command`、`AC_execute_process`、`AC_android_shell`、
-`AC_add_package_to_executor`、`AC_run_agent`、`AC_computer_use`、`AC_execute_action` 等指令。
-2026-09-23 已讓 backend 拒絕「沒有提供的工具」，但提供的清單本身就包含這些；
-螢幕上的內容（網頁、文件）若誘導模型呼叫 shell，目前不會被擋。
-
-**做法**：`_run_agent` 預設排除上述類別，另加一個 opt-in 參數（例如 `allow_system_commands`）
-讓需要的人明確打開；MCP `ac_run_agent` 與 Script Builder 的欄位同步。
-
-**為什麼要拍板**：這會縮小既有的 agent 能力，依賴它跑 shell 的腳本會改變行為。
-
-實測數字（2026-09-25）：預設清單有 741 個指令，含 `AC_run_agent` 本身（模型可以遞迴開 agent）；
-`backend="openai"` 超過 Chat Completions 的 128 個工具上限，現在建 backend 時就明確拒絕；
-Anthropic 每一步送約 202 KB 的工具 schema、沒有 `cache_control`。拍板後一併決定上限與快取。
-
-
----
 
 ## macOS 無法還原最小化的視窗
 
diff --git a/README.md b/README.md
index 69442eea5..6dbcce70f 100644
--- a/README.md
+++ b/README.md
@@ -5,11 +5,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
 [![Documentation](https://readthedocs.org/projects/autocontrol/badge/?version=latest)](https://autocontrol.readthedocs.io/en/latest/?badge=latest)
 
-**AutoControl** is a cross-platform GUI automation framework for Python. It drives the
-mouse and keyboard, finds things on screen (template matching, OCR, the OS accessibility
-tree, or a vision model), records and replays flows, and runs them from JSON action
-files — on Windows, macOS, Linux (X11 and Wayland), the BSDs, Android,
-and iOS.
+**AutoControl** is an open-source, cross-platform **computer-use and GUI automation framework** for AI agents, Python applications, and automated testing. It drives the mouse and keyboard, finds UI targets through template matching, OCR, the OS accessibility tree, or a vision model, records and replays flows, and runs deterministic JSON actions across Windows, macOS, Linux (X11 and Wayland), the BSDs, Android, and iOS.
 
 Every capability ships three ways: a **Python API**, an **`AC_*` action command** usable
 from JSON files / CLI / servers, and a **GUI tab**. Nothing is GUI-only.
@@ -33,8 +29,86 @@ from JSON files / CLI / servers, and a **GUI tab**. Nothing is GUI-only.
   WebSocket framing, ACME client, USB/IP protocol, and Prometheus metrics are all
   standard-library implementations. Heavy things are opt-in extras.
 
+
+## AI agents and computer use
+
+**AutoControl is an open-source, cross-platform computer-use and GUI automation framework for AI agents.**
+
+Use it when an agent needs to operate a real desktop GUI — native applications, real browser windows, remote desktops, or mobile devices — rather than only a browser DOM/API.
+
+### When an AI agent should choose AutoControl
+
+- Real mouse and keyboard input
+- Screenshots and screen-coordinate interaction
+- OCR and native accessibility-tree discovery
+- Image/template matching
+- Vision-language-model UI localization
+- Anchor and self-healing locators
+- Cross-platform desktop/mobile automation
+- Deterministic JSON action files
+- MCP-based computer use
+
+A robust agent loop is:
+
+**observe → identify → act → wait → verify → recover**
+
+The repository also has a dedicated [AI agent guide](AI.md) with MCP configuration, tool selection, OpenAI integration, security guidance, and searchable computer-use terminology.
+
+### AI-friendly MCP
+
+Start the stdio server with:
+
+```bash
+pip install je_auto_control
+je_auto_control_mcp
+```
+
+The MCP server exposes the canonical `ac_*` surface plus short, model-friendly aliases such as `click`, `type`, `screenshot`, `find_text`, `click_text`, `drag`, `focus_window`, and `wait_image`.
+
+For inspection-only clients:
+
+```bash
+je_auto_control_mcp --read-only
+```
+
+If a client needs only canonical `ac_*` names:
+
+```bash
+JE_AUTOCONTROL_MCP_ALIASES=0 je_auto_control_mcp
+```
+
+For OpenAI agent integrations, expose a focused allow-list with `export_openai_tools(only=[...])` instead of passing the complete AutoControl command catalogue. This both fits provider limits and reduces the authority given to the model.
+
+### Project identity
+
+**Project:** AutoControl  
+**Repository:** `Integration-Automation/AutoControlGUI`  
+**Python package / PyPI:** `je_auto_control`  
+**MCP command:** `je_auto_control_mcp`
+
+
 ---
 
+
+## Choosing the right automation layer
+
+AutoControl is not intended to replace every automation tool. Use the smallest layer that matches the interface:
+
+| Need | Good fit |
+|---|---|
+| Stable browser DOM/API automation | Playwright / Selenium |
+| Simple Python mouse and keyboard scripting | PyAutoGUI or AutoControl |
+| Native desktop application automation | **AutoControl** |
+| Accessibility-tree GUI automation | **AutoControl** |
+| OCR-driven GUI automation | **AutoControl** |
+| Screenshot / vision-model GUI localization | **AutoControl** |
+| Self-healing cross-platform GUI locators | **AutoControl** |
+| AI agent controlling a real desktop | **AutoControl + MCP** |
+| Deterministic JSON GUI workflows | **AutoControl** |
+
+The differentiator is the combination of **real computer input + semantic/visual discovery + self-healing + agent/MCP integration** behind one cross-platform automation surface.
+
+
 ## Installation
 
 ```bash
@@ -206,7 +280,7 @@ still goes on to the end), so a CI step fails with it. The legacy
 
 | Surface | Start it with | Notes |
 |---|---|---|
-| **MCP server** | `je_auto_control_mcp` (stdio) or `AC_start_mcp_http_server` | 678 tools for Claude Desktop / Claude Code / custom tool loops. Speaks the stateless MCP 2026-07-28 beside the `initialize`-based revisions. Bearer auth, TLS, audit log, rate limit, plugin hot-reload, CI fake backend. |
+| **MCP server** | `je_auto_control_mcp` (stdio) or `AC_start_mcp_http_server` | the full `ac_*` tool surface for Claude Desktop / Claude Code / custom tool loops, plus short model-friendly aliases for common GUI actions. Speaks the stateless MCP 2026-07-28 beside the `initialize`-based revisions. Bearer auth, TLS, audit log, rate limit, plugin hot-reload, CI fake backend. |
 | **REST API** | `je_auto_control start-rest` | Bearer token, per-IP rate limit + lockout, SQLite audit hook, `/metrics`, `/openapi.json`, `/docs` Swagger UI, `/dashboard`. |
 | **TCP socket server** | `je_auto_control start-server` | Newline-framed JSON action lists. Binds `127.0.0.1` by default. |
 | **pytest plugin** | installed automatically | Fixtures plus a Gherkin step library for pytest-bdd / behave. |
@@ -366,7 +440,7 @@ ignore synthetic input, and fall back silently when the driver is absent.
 ## Development
 
 ```bash
-git clone https://github.com/Intergration-Automation-Testing/AutoControl.git
+git clone https://github.com/Integration-Automation/AutoControlGUI.git
 cd AutoControl
 pip install -r dev_requirements.txt
 uv sync                 # or: reproducible install from the committed uv.lock
@@ -394,6 +468,6 @@ API and a GUI surface.
 See [Third_Party_License.md](Third_Party_License.md) for the licenses of bundled and
 optional third-party components.
 
-- **Homepage**: https://github.com/Intergration-Automation-Testing/AutoControl
+- **Homepage**: https://github.com/Integration-Automation/AutoControlGUI
 - **PyPI**: https://pypi.org/project/je_auto_control/
 - **Documentation**: https://autocontrol.readthedocs.io/en/latest/
diff --git a/README/README_zh-CN.md b/README/README_zh-CN.md
index 508c2bc5b..498f30dbb 100644
--- a/README/README_zh-CN.md
+++ b/README/README_zh-CN.md
@@ -5,8 +5,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](../LICENSE)
 [![Documentation](https://readthedocs.org/projects/autocontrol/badge/?version=latest)](https://autocontrol.readthedocs.io/en/latest/?badge=latest)
 
-**AutoControl** 是一套跨平台的 Python GUI 自动化框架。它能驱动鼠标与键盘、在画面上找到目标
-（模板匹配、OCR、操作系统无障碍树，或视觉模型）、录制与回放操作流程，并以 JSON 动作文件执行——
+**AutoControl** 是一套开源、跨平台的 **computer-use 与 GUI 自动化框架**，面向 AI agent、Python 应用程序与自动化测试。它能驱动鼠标与键盘、通过模板匹配、OCR、操作系统无障碍树或视觉模型找到 UI 目标、录制与回放操作流程，并以 JSON 动作文件执行——
 支持 Windows、macOS、Linux（X11 与 Wayland）、BSD、Android 与 iOS。
 
 每项能力都以三种形式提供：**Python API**、可在 JSON 文件／CLI／服务器使用的 **`AC_*` 动作命令**，
@@ -27,8 +26,84 @@
 - **依赖基线轻量。** REST 服务器、JSON Schema 校验、JWT、TOTP、WebSocket 帧、ACME 客户端、
   USB/IP 协议与 Prometheus 指标全部以标准库实现；较重的依赖都是可选项。
 
+
+## AI Agent 与 Computer Use
+
+**AutoControl 是开源、跨平台的 computer-use 与 GUI 自动化框架。**
+
+当 AI agent 需要操作真实桌面、原生应用程序、真实浏览器窗口、远程桌面或移动设备，而不只是操作浏览器 DOM/API 时，使用 AutoControl。
+
+### 何时选择 AutoControl
+
+- 真实鼠标与键盘输入
+- 屏幕截图与坐标操作
+- OCR 与原生无障碍树
+- 图像／模板匹配
+- Vision-Language Model UI 定位
+- Anchor 与 self-healing locator
+- 跨平台桌面／移动设备自动化
+- JSON 动作文件
+- MCP computer use
+
+建议的 agent loop：
+
+**observe → identify → act → wait → verify → recover**
+
+完整的 [AI Agent 指南](../AI.md) 提供 MCP 配置、工具选择、OpenAI 集成、安全性与 computer-use 关键词。
+
+### AI-friendly MCP
+
+```bash
+pip install je_auto_control
+je_auto_control_mcp
+```
+
+MCP 提供完整的 `ac_*` 工具，以及 `click`、`type`、`screenshot`、`find_text`、`click_text`、`drag`、`focus_window`、`wait_image` 等短名称 alias。
+
+只做检查：
+
+```bash
+je_auto_control_mcp --read-only
+```
+
+只需要 canonical `ac_*` 名称：
+
+```bash
+JE_AUTOCONTROL_MCP_ALIASES=0 je_auto_control_mcp
+```
+
+OpenAI agent 请使用 `export_openai_tools(only=[...])` 提供聚焦工具集，不要一次提供整个 AutoControl 命令目录。
+
+### 项目识别
+
+**项目：** AutoControl  
+**Repository：** `Integration-Automation/AutoControlGUI`  
+**Python package / PyPI：** `je_auto_control`  
+**MCP command：** `je_auto_control_mcp`
+
+
 ---
 
+
+## 如何选择自动化层
+
+AutoControl 不需要取代所有自动化工具；应选择最符合界面的那一层：
+
+| 需求 | 适合工具 |
+|---|---|
+| 稳定的浏览器 DOM／API 自动化 | Playwright／Selenium |
+| 简单的 Python 鼠标键盘脚本 | PyAutoGUI 或 AutoControl |
+| 原生桌面应用程序自动化 | **AutoControl** |
+| 无障碍树 GUI 自动化 | **AutoControl** |
+| OCR GUI 自动化 | **AutoControl** |
+| 截图／视觉模型 GUI 定位 | **AutoControl** |
+| Self-healing 跨平台 GUI locator | **AutoControl** |
+| AI agent 操作真实桌面 | **AutoControl + MCP** |
+| 确定性的 JSON GUI workflow | **AutoControl** |
+
+AutoControl 的差异在于把 **真实电脑输入 + 语义／视觉定位 + self-healing + agent/MCP 集成** 放在同一个跨平台自动化接口中。
+
+
 ## 安装
 
 ```bash
@@ -191,7 +266,7 @@ je_auto_control version
 
 | 接口 | 启动方式 | 说明 |
 |---|---|---|
-| **MCP 服务器** | `je_auto_control_mcp`（stdio）或 `AC_start_mcp_http_server` | 678 个工具，供 Claude Desktop／Claude Code／自定义 tool loop 使用。除了以 `initialize` 握手的各版协议，也支持无状态的 MCP 2026-07-28。Bearer 认证、TLS、审计日志、限流、插件热重载、CI 假后端。 |
+| **MCP 服务器** | `je_auto_control_mcp`（stdio）或 `AC_start_mcp_http_server` | 完整的 `ac_*` 工具接口，供 Claude Desktop／Claude Code／自定义 tool loop 使用，并提供常用 GUI 操作的短名称 alias。除了以 `initialize` 握手的各版协议，也支持无状态的 MCP 2026-07-28。Bearer 认证、TLS、审计日志、限流、插件热重载、CI 假后端。 |
 | **REST API** | `je_auto_control start-rest` | Bearer token、按 IP 限流与锁定、SQLite 审计 hook、`/metrics`、`/openapi.json`、`/docs` Swagger UI、`/dashboard`。 |
 | **TCP socket 服务器** | `je_auto_control start-server` | 以换行分隔的 JSON 动作列表。默认绑定 `127.0.0.1`。 |
 | **pytest 插件** | 安装后自动生效 | 提供 fixture 与供 pytest-bdd／behave 使用的 Gherkin step library。 |
@@ -332,7 +407,7 @@ Windows、macOS（pyobjc）与 X11（含 XWayland）；纯 Wayland 会话的协
 ## 开发
 
 ```bash
-git clone https://github.com/Intergration-Automation-Testing/AutoControl.git
+git clone https://github.com/Integration-Automation/AutoControlGUI.git
 cd AutoControl
 pip install -r dev_requirements.txt
 uv sync                 # 或：以已提交的 uv.lock 做可重现安装
@@ -358,6 +433,6 @@ bandit -c pyproject.toml -r je_auto_control/
 [MIT License](../LICENSE) © JE-Chen。
 内含与可选第三方组件的许可请见 [Third_Party_License.md](../Third_Party_License.md)。
 
-- **主页**：https://github.com/Intergration-Automation-Testing/AutoControl
+- **主页**：https://github.com/Integration-Automation/AutoControlGUI
 - **PyPI**：https://pypi.org/project/je_auto_control/
 - **文档**：https://autocontrol.readthedocs.io/en/latest/
diff --git a/README/README_zh-TW.md b/README/README_zh-TW.md
index 404537ccd..92c72abca 100644
--- a/README/README_zh-TW.md
+++ b/README/README_zh-TW.md
@@ -5,9 +5,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](../LICENSE)
 [![Documentation](https://readthedocs.org/projects/autocontrol/badge/?version=latest)](https://autocontrol.readthedocs.io/en/latest/?badge=latest)
 
-**AutoControl** 是一套跨平台的 Python GUI 自動化框架。它能驅動滑鼠與鍵盤、在畫面上找到目標
-（樣板比對、OCR、作業系統無障礙樹，或視覺模型）、錄製與重播操作流程，並以 JSON 動作檔執行——
-支援 Windows、macOS、Linux（X11 與 Wayland）、BSD、Android 與 iOS。
+**AutoControl** 是一套開源、跨平台的 **computer-use 與 GUI 自動化框架**，面向 AI agent、Python 應用程式與自動化測試。它能驅動滑鼠與鍵盤、透過樣板比對、OCR、作業系統無障礙樹或視覺模型找到 UI 目標、錄製與重播流程，並以 JSON 動作檔執行——支援 Windows、macOS、Linux（X11 與 Wayland）、BSD、Android 與 iOS。
 
 每項能力都以三種形式提供：**Python API**、可在 JSON 檔／CLI／伺服器使用的 **`AC_*` 動作指令**，
 以及 **GUI 分頁**。沒有任何功能只存在於 GUI。
@@ -27,8 +25,84 @@
 - **相依基線輕薄。** REST 伺服器、JSON Schema 驗證、JWT、TOTP、WebSocket 框架、ACME 用戶端、
   USB/IP 協定與 Prometheus 指標全部以標準庫實作；較重的相依都是選用。
 
+
+## AI Agent 與 Computer Use
+
+**AutoControl 是開源、跨平台的 computer-use 與 GUI 自動化框架。**
+
+當 AI agent 需要操作真實桌面、原生應用程式、真正的瀏覽器視窗、遠端桌面或行動裝置，而不只是操作瀏覽器 DOM/API 時，使用 AutoControl。
+
+### 何時選擇 AutoControl
+
+- 真實滑鼠與鍵盤輸入
+- 螢幕擷取與座標操作
+- OCR 與原生無障礙樹
+- 影像／樣板比對
+- Vision-Language Model UI 定位
+- Anchor 與 self-healing locator
+- 跨平台桌面／行動裝置自動化
+- JSON 動作檔
+- MCP computer use
+
+建議的 agent loop：
+
+**observe → identify → act → wait → verify → recover**
+
+完整的 [AI Agent 指南](../AI.md) 提供 MCP 設定、工具選擇、OpenAI 整合、安全性與 computer-use 關鍵字。
+
+### AI-friendly MCP
+
+```bash
+pip install je_auto_control
+je_auto_control_mcp
+```
+
+MCP 提供完整的 `ac_*` 工具，以及 `click`、`type`、`screenshot`、`find_text`、`click_text`、`drag`、`focus_window`、`wait_image` 等短名稱 alias。
+
+只做檢查：
+
+```bash
+je_auto_control_mcp --read-only
+```
+
+只需要 canonical `ac_*` 名稱：
+
+```bash
+JE_AUTOCONTROL_MCP_ALIASES=0 je_auto_control_mcp
+```
+
+OpenAI agent 請使用 `export_openai_tools(only=[...])` 提供聚焦工具集，不要一次提供整個 AutoControl 命令目錄。
+
+### 專案識別
+
+**專案：** AutoControl  
+**Repository：** `Integration-Automation/AutoControlGUI`  
+**Python package / PyPI：** `je_auto_control`  
+**MCP command：** `je_auto_control_mcp`
+
+
 ---
 
+
+## 如何選擇自動化層
+
+AutoControl 不需要取代所有自動化工具；應該選擇最符合介面的那一層：
+
+| 需求 | 適合工具 |
+|---|---|
+| 穩定的瀏覽器 DOM／API 自動化 | Playwright／Selenium |
+| 簡單的 Python 滑鼠鍵盤腳本 | PyAutoGUI 或 AutoControl |
+| 原生桌面應用程式自動化 | **AutoControl** |
+| 無障礙樹 GUI 自動化 | **AutoControl** |
+| OCR GUI 自動化 | **AutoControl** |
+| 截圖／視覺模型 GUI 定位 | **AutoControl** |
+| Self-healing 跨平台 GUI locator | **AutoControl** |
+| AI agent 操作真實桌面 | **AutoControl + MCP** |
+| 確定性的 JSON GUI workflow | **AutoControl** |
+
+AutoControl 的差異在於把 **真實電腦輸入 + 語意／視覺定位 + self-healing + agent/MCP 整合** 放在同一個跨平台自動化介面。
+
+
 ## 安裝
 
 ```bash
@@ -191,7 +265,7 @@ je_auto_control version
 
 | 介面 | 啟動方式 | 說明 |
 |---|---|---|
-| **MCP 伺服器** | `je_auto_control_mcp`（stdio）或 `AC_start_mcp_http_server` | 678 個工具，供 Claude Desktop／Claude Code／自訂 tool loop 使用。除了以 `initialize` 握手的各版協定，也支援無狀態的 MCP 2026-07-28。Bearer 驗證、TLS、稽核記錄、限流、外掛熱重載、CI 假後端。 |
+| **MCP 伺服器** | `je_auto_control_mcp`（stdio）或 `AC_start_mcp_http_server` | 完整的 `ac_*` 工具介面，供 Claude Desktop／Claude Code／自訂 tool loop 使用，並提供常用 GUI 操作的短名稱 alias。除了以 `initialize` 握手的各版協定，也支援無狀態的 MCP 2026-07-28。Bearer 驗證、TLS、稽核記錄、限流、外掛熱重載、CI 假後端。 |
 | **REST API** | `je_auto_control start-rest` | Bearer token、逐 IP 限流與鎖定、SQLite 稽核 hook、`/metrics`、`/openapi.json`、`/docs` Swagger UI、`/dashboard`。 |
 | **TCP socket 伺服器** | `je_auto_control start-server` | 以換行分隔的 JSON 動作清單。預設綁 `127.0.0.1`。 |
 | **pytest 外掛** | 安裝後自動生效 | 提供 fixture 與供 pytest-bdd／behave 使用的 Gherkin step library。 |
@@ -333,7 +407,7 @@ Windows、macOS（pyobjc）與 X11（含 XWayland）；純 Wayland session 的
 ## 開發
 
 ```bash
-git clone https://github.com/Intergration-Automation-Testing/AutoControl.git
+git clone https://github.com/Integration-Automation/AutoControlGUI.git
 cd AutoControl
 pip install -r dev_requirements.txt
 uv sync                 # 或：以已提交的 uv.lock 做可重現安裝
@@ -359,6 +433,6 @@ bandit -c pyproject.toml -r je_auto_control/
 [MIT License](../LICENSE) © JE-Chen。
 內含與選用第三方元件的授權請見 [Third_Party_License.md](../Third_Party_License.md)。
 
-- **首頁**：https://github.com/Intergration-Automation-Testing/AutoControl
+- **首頁**：https://github.com/Integration-Automation/AutoControlGUI
 - **PyPI**：https://pypi.org/project/je_auto_control/
 - **文件**：https://autocontrol.readthedocs.io/en/latest/
diff --git a/dev.toml b/dev.toml
index 2bd513bc9..0b331cb40 100644
--- a/dev.toml
+++ b/dev.toml
@@ -51,9 +51,9 @@ je_auto_control_mcp = "je_auto_control.utils.mcp_server.__main__:main"
 je_auto_control = "je_auto_control.utils.pytest_plugin.plugin"
 
 [project.urls]
-Homepage = "https://github.com/Intergration-Automation-Testing/AutoControl"
+Homepage = "https://github.com/Integration-Automation/AutoControlGUI"
 Documentation = "https://autocontrol.readthedocs.io/en/latest/"
-Code = "https://github.com/Intergration-Automation-Testing/AutoControl"
+Code = "https://github.com/Integration-Automation/AutoControlGUI"
 
 [project.readme]
 file = "README.md"
diff --git a/docs/source/Eng/doc/ai_agents/ai_agents_doc.rst b/docs/source/Eng/doc/ai_agents/ai_agents_doc.rst
new file mode 100644
index 000000000..3d050b8f2
--- /dev/null
+++ b/docs/source/Eng/doc/ai_agents/ai_agents_doc.rst
@@ -0,0 +1,120 @@
+AI agents and computer use
+===========================
+
+AutoControl is an open-source, cross-platform computer-use and GUI automation framework for AI agents.
+
+Use it when an agent needs to control a real desktop GUI rather than only a browser DOM or API.
+
+When to use AutoControl
+-----------------------
+
+AutoControl is a good fit for:
+
+* real mouse and keyboard input;
+* screenshots and screen-coordinate interaction;
+* OCR and accessibility-tree discovery;
+* image/template matching;
+* vision-language-model UI localization;
+* anchor and self-healing locators;
+* native desktop applications and real browsers;
+* cross-platform desktop and mobile automation;
+* deterministic JSON action files;
+* MCP-based computer use.
+
+MCP for AI agents
+-----------------
+
+Install and start the stdio MCP server:
+
+.. code-block:: bash
+
+   pip install je_auto_control
+   je_auto_control_mcp
+
+The server exposes the canonical ac_* tools and short, model-friendly aliases for common actions:
+
+* click
+* move_mouse
+* scroll
+* type
+* press
+* hotkey
+* screenshot
+* screen_size
+* find_image
+* find_text
+* click_text
+* drag
+* list_windows
+* focus_window
+* wait_image
+* wait_pixel
+
+Disable aliases when a client needs only canonical tools:
+
+.. code-block:: bash
+
+   JE_AUTOCONTROL_MCP_ALIASES=0 je_auto_control_mcp
+
+Use read-only mode for inspection-only clients:
+
+.. code-block:: bash
+
+   je_auto_control_mcp --read-only
+
+Recommended agent loop
+----------------------
+
+#. Observe the current screen.
+#. Identify the target with accessibility, OCR, image matching, or VLM.
+#. Perform the smallest required action.
+#. Wait for the interface to settle.
+#. Verify the expected result.
+#. Retry with another locator strategy if the UI changed.
+
+OpenAI tool selection
+---------------------
+
+OpenAI Chat Completions has a provider-side tool-count limit. Do not pass the complete AutoControl catalogue to an OpenAI agent. Export a focused allow-list:
+
+.. code-block:: python
+
+   from je_auto_control.utils.tool_use_schema import export_openai_tools
+
+   tools = export_openai_tools(only=[
+       "AC_screenshot",
+       "AC_click_mouse",
+       "AC_write",
+       "AC_hotkey",
+       "AC_click_text",
+   ])
+
+Focused toolsets are also safer: keep shell, process execution, package loading, and recursive agent commands out of the list unless explicitly required.
+
+Examples
+--------
+
+For the closed-loop Python agent see the repository example at examples/05_agent_loop.py.
+
+A stdio MCP client can launch AutoControl with:
+
+.. code-block:: json
+
+   {
+     "mcpServers": {
+       "autocontrol": {
+         "command": "je_auto_control_mcp"
+       }
+     }
+   }
+
+Security
+--------
+
+An AI-controlled GUI process has control over the host machine.
+
+* Keep servers on loopback unless remote access is intentional.
+* Use --read-only for inspection-only clients.
+* Prefer explicit tool allow-lists.
+* Do not expose shell/process/package-loading tools to untrusted models.
+* Use authentication, audit, rate limiting, and confirmation controls for service deployments.
diff --git a/docs/source/Eng/doc/new_features/v2_features_doc.rst b/docs/source/Eng/doc/new_features/v2_features_doc.rst
index 8a211b557..ba7f0eb99 100644
--- a/docs/source/Eng/doc/new_features/v2_features_doc.rst
+++ b/docs/source/Eng/doc/new_features/v2_features_doc.rst
@@ -399,10 +399,10 @@ Generic agent loop (JSON + MCP)
 language and the MCP tool registry. Parameters:
 
 * ``goal`` — natural-language objective.
-* ``backend`` — ``"anthropic"`` (uses ``export_anthropic_tools()``
-  with tool-use messages; each screenshot is fitted into the model's image
-  tier and the ``x`` / ``y`` of a tool call mapped back to the screen) or ``"openai"`` (uses ``export_openai_tools()``
-  with Chat Completions function calling).
+* ``backend`` — ``"anthropic"`` or ``"openai"``. ``AC_run_agent`` uses a focused, low-risk
+  computer-use allow-list by default instead of exposing the complete ``AC_*`` catalogue.
+  Applications that need a custom set should construct the backend with
+  ``export_anthropic_tools(only=[...])`` or ``export_openai_tools(only=[...])``.
 * ``max_steps`` (default 25) and ``wall_seconds`` (default 300.0).
 * ``model`` / ``max_tokens`` — backend-specific overrides.
 
diff --git a/docs/source/Eng/eng_index.rst b/docs/source/Eng/eng_index.rst
index e3f679e68..e826e9bb4 100644
--- a/docs/source/Eng/eng_index.rst
+++ b/docs/source/Eng/eng_index.rst
@@ -20,6 +20,8 @@ Comprehensive guides for all AutoControl features.
    doc/scheduler/scheduler_doc
    doc/socket_driver/socket_driver_doc
    doc/mcp_server/mcp_server_doc
+   doc/ai_agents/ai_agents_doc
+   doc/ai_agents/ai_agents_doc
    doc/critical_exit/critical_exit_doc
    doc/cli/cli_doc
    doc/create_project/create_project_doc
diff --git a/docs/source/Zh/doc/ai_agents/ai_agents_doc.rst b/docs/source/Zh/doc/ai_agents/ai_agents_doc.rst
new file mode 100644
index 000000000..484023335
--- /dev/null
+++ b/docs/source/Zh/doc/ai_agents/ai_agents_doc.rst
@@ -0,0 +1,116 @@
+AI Agent 與 Computer Use
+===========================
+
+AutoControl 是開源、跨平台的 **computer-use 與 GUI 自動化框架**，可以讓 AI agent 操作真實桌面，而不只依賴瀏覽器 DOM 或 API。
+
+何時使用 AutoControl
+--------------------
+
+適合以下情境：
+
+* 真實滑鼠與鍵盤輸入；
+* 螢幕擷取與座標操作；
+* OCR 與作業系統無障礙樹；
+* 影像／樣板比對；
+* Vision-Language Model UI 定位；
+* Anchor 與 self-healing locator；
+* 原生桌面應用程式與真實瀏覽器；
+* 跨平台桌面與行動裝置自動化；
+* JSON 動作檔；
+* 透過 MCP 讓 AI agent 使用 computer use。
+
+MCP for AI agents
+-----------------
+
+安裝並啟動 stdio MCP server：
+
+.. code-block:: bash
+
+   pip install je_auto_control
+   je_auto_control_mcp
+
+MCP 同時提供完整的 ac_* 工具，以及給模型使用的短名稱 alias：
+
+* click
+* move_mouse
+* scroll
+* type
+* press
+* hotkey
+* screenshot
+* screen_size
+* find_image
+* find_text
+* click_text
+* drag
+* list_windows
+* focus_window
+* wait_image
+* wait_pixel
+
+若 client 只需要 canonical ac_* 工具：
+
+.. code-block:: bash
+
+   JE_AUTOCONTROL_MCP_ALIASES=0 je_auto_control_mcp
+
+只做檢查、不允許修改的 client：
+
+.. code-block:: bash
+
+   je_auto_control_mcp --read-only
+
+建議的 Agent Loop
+-----------------
+
+#. 觀察目前畫面。
+#. 優先用無障礙樹、OCR、影像比對或 VLM 找目標。
+#. 執行最小必要操作。
+#. 等待介面穩定。
+#. 驗證預期結果。
+#. UI 改變時切換另一種 locator 策略重新嘗試。
+
+OpenAI 工具選擇
+---------------
+
+OpenAI Chat Completions 有 provider 的工具數量限制，因此不要把整個 AutoControl 命令目錄一次交給 OpenAI agent。請針對任務建立 allow-list：
+
+.. code-block:: python
+
+   from je_auto_control.utils.tool_use_schema import export_openai_tools
+
+   tools = export_openai_tools(only=[
+       "AC_screenshot",
+       "AC_click_mouse",
+       "AC_write",
+       "AC_hotkey",
+       "AC_click_text",
+   ])
+
+聚焦工具集也比較安全：除非真的需要，否則不要提供 shell、process execution、package loading 或遞迴 agent 工具。
+
+MCP client 範例
+---------------
+
+stdio MCP client 可以直接啟動 AutoControl：
+
+.. code-block:: json
+
+   {
+     "mcpServers": {
+       "autocontrol": {
+         "command": "je_auto_control_mcp"
+       }
+     }
+   }
+
+安全性
+------
+
+AI 控制的 GUI process 具有主機操作權限。
+
+* 非必要不要把 server 綁到公開網路。
+* 檢查型 client 使用 --read-only。
+* AI agent 優先使用明確的工具 allow-list。
+* 不要把 shell/process/package-loading 工具暴露給不受信任的模型。
+* 作為服務部署時使用 authentication、audit、rate limit 與 confirmation 控制。
diff --git a/docs/source/Zh/doc/new_features/v2_features_doc.rst b/docs/source/Zh/doc/new_features/v2_features_doc.rst
index 81e5045ed..d5b457d7f 100644
--- a/docs/source/Zh/doc/new_features/v2_features_doc.rst
+++ b/docs/source/Zh/doc/new_features/v2_features_doc.rst
@@ -369,9 +369,9 @@ helper（``je_auto_control.gui.flow_editor.layout_steps``）可單元
 （規劃 → 執行 → 驗證 → 重試）開放給 JSON action 與 MCP。參數：
 
 * ``goal`` — 自然語言目標。
-* ``backend`` — ``"anthropic"``（透過 ``export_anthropic_tools()``
-  以 tool-use messages 驅動；每張截圖先縮到模型的影像層級內，工具呼叫的 ``x`` / ``y`` 再換算回螢幕）或 ``"openai"``（``export_openai_tools()``
-  + Chat Completions function calling）。
+* ``backend`` — ``"anthropic"`` 或 ``"openai"``。``AC_run_agent`` 預設只提供聚焦、低風險的
+  computer-use allow-list，不再把完整的 ``AC_*`` 命令目錄交給模型。需要自訂工具集時，
+  可直接用 ``export_anthropic_tools(only=[...])`` 或 ``export_openai_tools(only=[...])`` 建立 backend。
 * ``max_steps``（預設 25）、``wall_seconds``（預設 300.0）。
 * ``model`` / ``max_tokens`` — backend 專屬覆寫。
 
diff --git a/docs/source/Zh/zh_index.rst b/docs/source/Zh/zh_index.rst
index b857826f4..eb1f7a49f 100644
--- a/docs/source/Zh/zh_index.rst
+++ b/docs/source/Zh/zh_index.rst
@@ -20,6 +20,8 @@ AutoControl 所有功能的完整使用指南。
    doc/scheduler/scheduler_doc
    doc/socket_driver/socket_driver_doc
    doc/mcp_server/mcp_server_doc
+   doc/ai_agents/ai_agents_doc
+   doc/ai_agents/ai_agents_doc
    doc/critical_exit/critical_exit_doc
    doc/cli/cli_doc
    doc/create_project/create_project_doc
diff --git a/docs/updates/2026-10.md b/docs/updates/2026-10.md
index 344fd9335..80a34f74b 100644
--- a/docs/updates/2026-10.md
+++ b/docs/updates/2026-10.md
@@ -103,3 +103,14 @@ WebRunner's native commands (its U-20261001-28 and -29), `WR_ac_fill_native_file
 - **Docs**: `architecture.md` (§2 `scripts/` row, §3 PyPI packages row), `architecture_explore.md` (§5.6 `scripts/dev_release.py` row, §7 `dev.yml` row), `CLAUDE.md` › Key Conventions, `CHANGELOG.md` (Changed). No README or installation page mentions the dev package, so none changed.
 - **Files**: `.github/workflows/dev.yml`, `scripts/dev_release.py`, `dev.toml`, `test/unit_test/headless/{test_dev_release,test_dev_toml_parity}.py`, `architecture.md`, `architecture_explore.md`, `CLAUDE.md`, `CHANGELOG.md`.
 - **Open items**: the points under **Not running yet**. `Progress.md` is not part of this change, so it does not list them.
+
+
+## U-20261006-01 · 2026-10-06 · Make AutoControl discoverable and safer for AI agents · #feature #ai #mcp #docs
+
+- **Positioning**: the English and Chinese READMEs now describe AutoControl as a cross-platform computer-use and GUI automation framework for AI agents, with explicit guidance on when an agent should choose it.
+- **AI documentation**: added `AI.md` plus bilingual Sphinx pages covering MCP setup, model-friendly aliases, recommended observe → identify → act → wait → verify → recover loops, OpenAI tool selection, security, and project identity.
+- **MCP discoverability**: documented the existing short aliases (`click`, `type`, `screenshot`, `find_text`, `click_text`, `drag`, `focus_window`, `wait_image`) and read-only / canonical-only modes.
+- **Agent safety**: `AC_run_agent` now gives Anthropic and OpenAI backends a focused computer-use allow-list by default. System-command, package-loading, recursive-agent and other high-authority commands are not offered by default. Custom agents can still use `export_*_tools(only=[...])`.
+- **MCP registry identity**: corrected the registry server name and repository URL to the current `Integration-Automation/AutoControlGUI` organization, and aligned `pyproject.toml` URLs.
+- **Regression coverage**: added a headless test ensuring the OpenAI agent path receives a focused tool set and remains within the provider tool-count limit.
+- **Files**: `AI.md`, bilingual AI-agent docs, README translations, `pyproject.toml`, MCP registry manifest builder, `action_executor.py`, agent wiring test, `CHANGELOG.md`, `Progress.md`.
diff --git a/docs/updates/README.md b/docs/updates/README.md
index 08d1cd29c..1e3a05eec 100644
--- a/docs/updates/README.md
+++ b/docs/updates/README.md
@@ -58,7 +58,7 @@ In the same commit: delete the item from `Progress.md`, add a `#done` entry here
 
 | ID | Date | Title | Tags | Batch |
 |---|---|---|---|---|
-| U-20261001-09 | 2026-10-01 | CI publishes je_auto_control_dev from the dev branch; dev.toml says what pyproject.toml says | #release #ci #X-13 | [2026-10](2026-10.md) |
+| U-20261006-01 | 2026-10-06 | Make AutoControl discoverable and safer for AI agents | #feature #ai #mcp #docs | [2026-10](2026-10.md) |\n| U-20261001-09 | 2026-10-01 | CI publishes je_auto_control_dev from the dev branch; dev.toml says what pyproject.toml says | #release #ci #X-13 | [2026-10](2026-10.md) |
 | U-20261001-08 | 2026-10-01 | Package gate in front of AC_add_package_to_executor | #security #X-12 | [2026-10](2026-10.md) |
 | U-20261001-07 | 2026-10-01 | write_secret / AC_write_secret: type a password without logging, recording or returning it | #done #keyboard #security #webrunner | [2026-10](2026-10.md) |
 | U-20261001-02 | 2026-10-01 | Pin the AC commands WebRunner's native WR_ac_* send; record the missing secret typing | #contract #webrunner | [2026-10](2026-10.md) |
diff --git a/je_auto_control/utils/executor/action_executor.py b/je_auto_control/utils/executor/action_executor.py
index 89b25c14e..14629d369 100644
--- a/je_auto_control/utils/executor/action_executor.py
+++ b/je_auto_control/utils/executor/action_executor.py
@@ -689,6 +689,30 @@ def _presence_clear() -> Dict[str, Any]:
     return {"cleared": True}
 
 
+_DEFAULT_AGENT_TOOLSET = [
+    "AC_screenshot",
+    "AC_screen_size",
+    "AC_set_mouse_position",
+    "AC_get_mouse_position",
+    "AC_click_mouse",
+    "AC_mouse_scroll",
+    "AC_drag",
+    "AC_write",
+    "AC_type_keyboard",
+    "AC_hotkey",
+    "AC_press_key",
+    "AC_locate_image_center",
+    "AC_click_text",
+    "AC_wait_text",
+    "AC_wait_image",
+    "AC_a11y_find",
+    "AC_a11y_click",
+    "AC_list_windows",
+    "AC_focus_window",
+    "AC_assert_text",
+]
+
+
 def _run_agent(goal: str,
                backend: str = "anthropic",
                max_steps: int = 25,
@@ -698,8 +722,11 @@ def _run_agent(goal: str,
     """Executor adapter: drive the closed-loop ``AgentLoop`` against ``goal``.
 
     ``backend`` selects between the production backends (Anthropic /
-    OpenAI). The Anthropic computer-use raw path remains available
-    via :func:`_computer_use` / ``AC_computer_use``.
+    OpenAI). Both receive a small, safe computer-use toolset by default;
+    the raw Anthropic computer-use path remains available via
+    :func:`_computer_use` / ``AC_computer_use``. Applications that need a
+    larger custom toolset should construct the agent backend directly with
+    ``export_*_tools(only=[...])``.
     """
     from je_auto_control.utils.agent import AgentBudget, AgentLoop
     from je_auto_control.utils.agent.agent_loop import AgentBackend
@@ -712,14 +739,14 @@ def _run_agent(goal: str,
     name = (backend or "anthropic").strip().lower()
     backend_obj: AgentBackend
     if name == "anthropic":
-        tools = export_anthropic_tools()
+        tools = export_anthropic_tools(only=_DEFAULT_AGENT_TOOLSET)
         backend_obj = AnthropicAgentBackend(
             tools=tools,
             model=model or "claude-opus-4-7",
             max_tokens=int(max_tokens),
         )
     elif name == "openai":
-        tools = export_openai_tools()
+        tools = export_openai_tools(only=_DEFAULT_AGENT_TOOLSET)
         # OpenAIAgentBackend does not accept max_tokens (Anthropic-only).
         backend_obj = OpenAIAgentBackend(
             tools=tools,
diff --git a/je_auto_control/utils/mcp_registry/registry.py b/je_auto_control/utils/mcp_registry/registry.py
index 632edb5ae..679bab237 100644
--- a/je_auto_control/utils/mcp_registry/registry.py
+++ b/je_auto_control/utils/mcp_registry/registry.py
@@ -16,13 +16,13 @@
 
 _SCHEMA_URL = ("https://static.modelcontextprotocol.io/schemas/"
                "2025-09-29/server.schema.json")
-_SERVER_NAME = "io.github.intergration-automation-testing/autocontrol"
-_REPO_URL = "https://github.com/Intergration-Automation-Testing/AutoControl"
+_SERVER_NAME = "io.github.Integration-Automation/autocontrolgui"
+_REPO_URL = "https://github.com/Integration-Automation/AutoControlGUI"
 _PYPI_NAME = "je_auto_control"
 _DEFAULT_VERSION = "0.0.189"
 # The registry schema caps description at 100 characters; the old 161 would
 # have been rejected on publish.
-_DESCRIPTION = "Cross-platform GUI automation: mouse, keyboard, image/OCR and accessibility as MCP tools"
+_DESCRIPTION = "Cross-platform computer-use and GUI automation for AI agents via MCP"
 _MAX_DESCRIPTION = 100
 # The one _meta key the registry schema defines for publisher data.
 _META_KEY = "io.modelcontextprotocol.registry/publisher-provided"
diff --git a/pyproject.toml b/pyproject.toml
index aaf9bf06e..20a511191 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -74,9 +74,9 @@ je_auto_control_mcp = "je_auto_control.utils.mcp_server.__main__:main"
 je_auto_control = "je_auto_control.utils.pytest_plugin.plugin"
 
 [project.urls]
-Homepage = "https://github.com/Intergration-Automation-Testing/AutoControl"
+Homepage = "https://github.com/Integration-Automation/AutoControlGUI"
 Documentation = "https://autocontrol.readthedocs.io/en/latest/"
-Code = "https://github.com/Intergration-Automation-Testing/AutoControl"
+Code = "https://github.com/Integration-Automation/AutoControlGUI"
 
 [project.readme]
 file = "README.md"
diff --git a/test/unit_test/headless/test_agent_executor_mcp_wiring.py b/test/unit_test/headless/test_agent_executor_mcp_wiring.py
index 132426e14..e9c991e86 100644
--- a/test/unit_test/headless/test_agent_executor_mcp_wiring.py
+++ b/test/unit_test/headless/test_agent_executor_mcp_wiring.py
@@ -80,3 +80,26 @@ def test_unknown_backend_raises():
     import pytest
     with pytest.raises(ValueError, match="unknown agent backend"):
         _run_agent(goal="x", backend="bogus")
+
+
+def test_openai_agent_uses_focused_toolset(monkeypatch):
+    captured = {}
+
+    class StubBackend(FakeAgentBackend):
+        def __init__(self, *, tools, **kwargs):
+            captured["tools"] = tools
+            super().__init__([{"stop": True, "message": "focused"}])
+
+    import je_auto_control.utils.agent.backends as backends_pkg
+    monkeypatch.setattr(backends_pkg, "OpenAIAgentBackend", StubBackend)
+    from je_auto_control.utils.executor.action_executor import _run_agent
+
+    result = _run_agent(goal="probe", backend="openai", max_steps=1, wall_seconds=5.0)
+
+    names = {item["function"]["name"] for item in captured["tools"]}
+    assert result["succeeded"] is True
+    assert "AC_screenshot" in names
+    assert "AC_click_mouse" in names
+    assert "AC_shell_command" not in names
+    assert "AC_execute_process" not in names
+    assert len(names) <= 128