What platforms does Touchpoint support?
Linux (AT-SPI2), macOS (Accessibility API), and Windows (UI Automation). Platform-specific dependencies are installed automatically via pip environment markers.
@Touchpoint-Labs
基本信息
Playwright for the entire OS. Give AI agents the ability to see, find, and interact with UI elements in any desktop application — native apps, Electron apps, and browsers. Cross-platform: Linux, macOS, Windows.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"touchpoint": {
"command": "touchpoint-mcp",
"args": []
}
}
}`apps`, `windows`, `find`, `elements`, `get_element`
`screenshot` (returns image data the LLM can see)
`click` (left/right/double), `set_value`, `set_numeric_value`, `focus`, `action`
`type_text`, `press_key` (single key or combo)
`mouse_move`, `scroll`
`activate_window`
`wait_for`, `wait_for_app`, `wait_for_window`
Touchpoint is a cross-platform Python library that reads and interacts with desktop UI through native accessibility APIs, shipping with an MCP server so LLM agents can control any desktop app. It provides structured element data (names, roles, states, positions) without needing pixel scraping or vision models.
Install with pip install touchpoint-py, then configure the MCP server in your client by adding the touchpoint-mcp command (see client setup details in the README). Use the library API for direct automation: import touchpoint as tp, then call functions like tp.find(), tp.click(), tp.elements(), and tp.wait_for().
Linux (AT-SPI2), macOS (Accessibility API), and Windows (UI Automation). Platform-specific dependencies are installed automatically via pip environment markers.
No. It reads the real accessibility tree directly, providing fast and reliable structured data without model inference.
Add the MCP server to your Claude config file: set `command` to `touchpoint-mcp`. If using a virtualenv, use the full path to the binary. The MCP server includes built-in instructions for LLM agents.
Yes, via Chrome DevTools Protocol (CDP). Launch the browser or Electron app with `--remote-debugging-port=9222` and configure CDP discovery or explicit ports. Touchpoint merges native UI and web content in a single `elements()` call.
Python 3.10+. On Linux, `xdotool` is needed for input (usually pre-installed). On macOS, grant Accessibility permission in System Settings. No dependencies are needed on Windows—it uses built-in COM APIs.
Official repository bringing RADAAR's social media and content management tools to AI agents like Cursor, VS Code, and ChatGPT. Built on the agent-plugins.org standard, it connects seamlessly to the MCP server. Schedule

Official OmniSocials MCP server — schedule and publish posts, stories, and reels across 11 platforms (Instagram, Facebook, LinkedIn, YouTube, TikTok, X, Pinterest, Bluesky, Threads, Mastodon, Google Business), plus media

Publish pages your agent writes to a private, shareable URL, then read, comment on and update them. A hosted remote MCP server (OAuth) that works with Claude, ChatGPT, Codex, Cursor and any MCP client.

Traceable is a document-style workspace that keeps your design records connected and visible. It replaces spreadsheets, wikis and disconnected tools with one place to author, trace, control, review and publish the docume
crm, invoicing, proposals, contracts, project management, client portal, small business, time tracking
评论