CloakBrowser MCP 是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
CloakBrowser MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
CloakBrowser MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/swimmwatch/cloakbrowser-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"cloakbrowser-mcp": {
"command": "npx",
"args": ["-y", "cloakbrowser-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 CloakBrowser MCP 执行以下任务... Claude: [自动调用 CloakBrowser MCP MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"cloakbrowser_mcp": {
"command": "npx",
"args": ["-y", "cloakbrowser-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="docs/assets/brand/logo-wordmark.svg" alt="CloakBrowser MCP" width="640" /> </p>
cloakbrowser-mcp is a drop-in Playwright MCP-compatible browser automation server with unchanged upstream tools, CloakBrowser Chromium, and production-ready npm, Docker, and Streamable HTTP packaging. It runs upstream @playwright/mcp as the canonical tool surface and points that runtime at CloakBrowser.
npx -y cloakbrowser-mcp@latest
Requires Node.js 22.13+ in the 22.x line, or Node.js 24+. Run diagnostics before wiring a client:
npx -y cloakbrowser-mcp@latest doctor
For Streamable HTTP instead of stdio:
npx -y cloakbrowser-mcp@latest --transport streamable-http --http-port 3000
See the generated CLI Reference for all flags.
docker run --rm --init -i \
-v "$PWD/artifacts:/data" \
swimmwatch/cloakbrowser-mcp:latest
For Streamable HTTP:
docker run --rm --init -p 127.0.0.1:3000:3000 \
-v "$PWD/artifacts:/data" \
swimmwatch/cloakbrowser-mcp:latest \
--transport streamable-http --http-host 0.0.0.0 --http-port 3000
The Docker image writes artifacts to /data and is published for linux/amd64 and linux/arm64. It defaults to CLOAK_PLAYWRIGHT_MCP_NO_SANDBOX=true for compatibility with containerized runtimes where Chromium sandboxing is often unavailable. If your host and container runtime support Chromium sandboxing, set CLOAK_PLAYWRIGHT_MCP_NO_SANDBOX=false; for untrusted pages, keep container network access and mounted host directories tightly scoped. The same tags are also available from ghcr.io/swimmwatch/cloakbrowser-mcp. See Docker for persistent profiles, extension mounts, HTTPS, and smoke-test examples, or use the reverse proxy recipe for a focused Streamable HTTP deployment.
{
"mcpServers": {
"cloakbrowser": {
"command": "docker",
"args": [
"run",
"--rm",
"--init",
"-i",
"-v",
"/tmp/cloakbrowser-artifacts:/data",
"swimmwatch/cloakbrowser-mcp:latest"
]
}
}
}
Run npx -y cloakbrowser-mcp@latest, connect Claude Desktop or Codex CLI, ask for web research, daily automation, or testing in plain English, and inspect the real browser result.
Documentation: swimmwatch.github.io/cloakbrowser-mcp · Comparison · Recipes
Use it when you need:
Cross-platform checks cover npm on Linux x64/arm64, macOS arm64/x64, and Windows x64 across Node.js 22 and 24-26. Docker images are built and smoke-tested for linux/amd64 and linux/arm64.
See @playwright/mcp vs cloakbrowser-mcp when deciding whether plain upstream Playwright MCP or CloakBrowser MCP fits a deployment better. The Recipes pages show task-focused setup paths for persistent login profiles, Chrome extensions, reverse proxies, regional QA, client connections, and CI smoke tests.
Use upstream PLAYWRIGHT_MCP_* variables for browser, artifacts, timeouts, network, and tool capability settings. Cloak-specific bridge toggles use CLOAK_PLAYWRIGHT_MCP_*. Select a Pro Preview browser build before startup with --release-channel preview or CLOAK_PLAYWRIGHT_MCP_RELEASE_CHANNEL=preview; the default is stable.
The common variable table now lives in Configuration. That page also covers persistent profiles, validated context options, Chrome extensions, Streamable HTTP metadata, and HTTPS/auth options. See GeoIP Proxy Matching for regional proxy behavior, Humanized Input Behavior for interaction realism, and Recipes for task-focused configurations.
{
"servers": {
"cloakbrowser": {
"type": "stdio",
"command": "npx",
"args": ["-y", "cloakbrowser-mcp@latest"]
}
}
}
高质量的MCP工具,支持Playwright浏览器自动化
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,CloakBrowser MCP 在MCP工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | cloakbrowser-mcp |
| 原始描述 | 开源MCP工具:⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool。⭐18 · TypeScript |
| Topics | mcpai-agentsbrowser-automationtypescript |
| GitHub | https://github.com/swimmwatch/cloakbrowser-mcp |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-06-26 · 更新时间:2026-06-26 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端