Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
AmrDab/clawdcursor
Local MCP server that gives any AI agent safe desktop control on Windows, macOS and Linux. Reads the screen as text and structure (accessibility + OCR) and acts by element name, with screenshots as the last resort. Multi-monitor aware, verifies every action, one safety gate.
根据公开文档整理，未运行实测；费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
上手GET STARTED
npm i -g clawdcursor选择与你的环境对应的方式。命令来自项目文档，未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查，未执行项目代码；扫描没有命中，不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
powershell -c "irm https://clawdcursor.com/install.ps1 | iex"
02控制浏览器Controls a browserreadme
The desktop-agent space is crowded. The closest **install-and-go** peers are [Windows-MCP](https://github.com/CursorTouch/Windows-MCP) and [
03控制浏览器Controls a browserSKILL.md
> 4. Existing browser automation (Playwright, Puppeteer) → use that.
04安装时执行脚本Runs a script during installpackage.json
postinstall: node scripts/verify-install.js || node -e "process.exit(0)" && node scripts/postinstall-native.js || node -e "process.exit(0)"
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
26 OCT 202626 OCT 2026
增长GROWTH
+0.0%+0.0%
406 → 406 stars · 8 个快照406 → 406 stars · 8 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
3 条外部提及3 external mentions
状态STATUS
持续活跃Active
HN_STORY · 4 points · 1 comments
HN_STORY · 2 points · 0 comments
HN_STORY · 2 points · 0 comments
依赖：Dependencies:@modelcontextprotocol/sdk, @nut-tree-fork/nut-js, commander, croner, dotenv, express, picocolors, playwright, sharp, ws, zod
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "claude-desktop",
"evidence": "readme: …y installed copy (global npm, Claude Desktop extension, Claude Code plugin…"
},
{
"agent": "codex",
"evidence": "readme: …sktop, Cursor, Windsurf, Zed, OpenAI Codex, or your own loop) the same w…"
},
{
"agent": "windsurf",
"evidence": "readme: …— Claude Code, Cursor, Windsurf, OpenClaw, the Claude Agent S…"
},
{
"agent": "cline",
"evidence": "readme: …· Windsurf · Claude Desktop · Cline · Gemini CLI** — the common `…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …rf · Claude Desktop · Cline · Gemini CLI** — the common `mcpServers` s…"
},
{
"agent": "vscode",
"evidence": "readme: …licitation (e.g. Claude Code, VS Code) also let you skip > `consent…"
},
{
"agent": "opencode",
"evidence": "readme: …artup_timeout_sec = 30 ``` **opencode** — `opencode.json` uses `mcp…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 7,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 9,
"productivity": 3
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "de, GPT, Gemini, Llama, Kimi, Ollama, …), credentials, model config. | | `sr",
"skillMdTotal": 2,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 1,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "2 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "server.json (MCP registry manifest)",
"weight": 0.85
},
{
"signal": "package.json depends on @modelcontextprotocol/sdk + MCP framing",
"weight": 0.8
},
{
"signal": "skills/ directory with 1 markdown files",
"weight": 0.75
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "README ships an mcpServers config for this server",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"SKILL.md",
"skills/clawdcursor/SKILL.md"
],
"skillMdFetched": 2
}