MCP工具 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。
MCP工具 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。
MCP工具 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/multiplex-ai/muggle-ai-works
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp--": {
"command": "npx",
"args": ["-y", "muggle-ai-works"]
}
}
}
# 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 MCP工具 执行以下任务... Claude: [自动调用 MCP工具 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": {
"mcp__": {
"command": "npx",
"args": ["-y", "muggle-ai-works"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
An open-source harness that drives your AI coding agent through the whole delivery cycle — design, build, test, acceptance — and closes the loop on GitHub and GitLab.
Coding agents are good at producing a diff. They are bad at knowing whether the diff works, whether it broke the login flow, and what still has to happen before a human can merge it. Muggle Works is the harness around the agent that answers those questions: it freezes requirements, delegates the design and build, runs the unit suite, drives a real browser through the affected user flows, opens the pull request with screenshots attached, and then keeps watching that PR — picking up review comments, red CI, and a stale base branch until the change is genuinely mergeable.
Works in Claude Code, Cursor, Codex, Windsurf, and any MCP client. Powered by Muggle Test.
---
/mdo "add a logout button" runs requirements → design → build → impact analysis → unit tests → browser acceptance → PR. You answer one questionnaire up front, then walk away.SKIP_AUTH flag.Claude Code — full plugin: skills, MCP tools, and the browser runner.
/plugin marketplace add https://github.com/multiplex-ai/muggle-ai-works
/plugin install muggleai@muggle-works
Cursor — npm install -g @muggleai/works. The postinstall writes ~/.cursor/mcp.json and syncs the muggle-* skills into ~/.cursor/skills/. Restart Cursor.
Codex, Windsurf, any other MCP client — install the package as above, then register the server:
{
"mcpServers": {
"muggle": {
"command": "muggle",
"args": ["serve"],
"env": {
"MUGGLE_MCP_PROMPT_SERVICE_TARGET": "production"
}
}
}
}
/mdo "Add a logout button to the header"
PRE-FLIGHT → repo: frontend · branch: users/me/logout-button · target: localhost:3000
REQUIREMENTS → Goal: logout button in header. AC: visible, ends session, redirects to /login.
BUILD → src/components/Header.tsx, src/hooks/useLogout.ts (+ unit tests)
IMPACT → affects "User Login" and "Session" flows
UNIT TESTS → 12/12 pass
ACCEPTANCE → 3/3 test cases pass · runId a1b2c3 · 14 screenshots
PULL REQUEST → #42 opened, walkthrough posted
WATCHER → armed on #42
Authentication starts on the first protected call: a browser opens with a verification code, you sign in, and the call continues. Credentials persist in ~/.muggle-ai/.
---
muggle init # Guided setup; saves preferences, offers the CI check muggle setup [--force] # Download or update the browser runner muggle upgrade [--check] # Install the latest runner version muggle versions # List installed runner versions muggle cleanup [--dry-run] # Remove old versions and obsolete skills muggle doctor # Diagnose installation problems
Environment targeting. Set MUGGLE_MCP_PROMPT_SERVICE_TARGET (production or dev) in the MCP server's env block. Mismatching it against the account you log in with is the usual cause of unauthorized_client.
Multi-repo cycles. Drop a muggle-repos.json in your working directory so a single request can span services:
[
{ "name": "frontend", "path": "/absolute/path/to/frontend", "testCommand": "pnpm test" },
{ "name": "backend", "path": "/absolute/path/to/backend", "testCommand": "pnpm test" }
]
Preferences. /mprefs (or muggle init) controls the gates — whether to use a worktree, rebase onto the base branch, run acceptance tests every cycle, open the PR automatically, and arm the watcher. Each gate takes always, ask, or never.
When installed as a Claude Code plugin, MCP configuration ships with the plugin (plugin/.mcp.json) — there is nothing to copy by hand.
---
108 tools across authentication, projects, use cases, test cases, scripts, workflows, local execution, reporting, secrets, billing, and administration. Call them directly from any MCP client to build your own pipeline.
Authentication — muggle-remote-auth-status, -login, -poll, -logout, plus -api-key-create, -list, -get, -revoke.
Projects — muggle-remote-project-create, -list, -get, -update, -delete, plus per-project rollups: -test-results-summary-get, -test-runs-summary-get, -test-scripts-summary-get.
| Use cases | Purpose |
|---|---|
muggle-remote-use-case-list / -get | Read use cases |
muggle-remote-use-case-create | Persist a fully-specified use case (no LLM) |
muggle-remote-use-case-create-from-prompts | Create from natural language |
muggle-remote-use-case-prompt-preview | Preview before creating |
muggle-remote-use-case-update-from-prompt | Regenerate from a new prompt |
muggle-remote-use-case-candidates-approve | Approve discovered candidates |
muggle-remote-use-case-bulk-preview-submit | Async batch preview (~50% cheaper) |
muggle-remote-use-case-delete | Delete (cascades to test cases + scripts) |
| Test cases | Purpose |
|---|---|
muggle-remote-test-case-list / -list-by-use-case / -get | Read test cases |
muggle-remote-test-case-create / -update / -delete | Manage test cases |
muggle-remote-test-case-generate-from-prompt | Generate from a prompt |
muggle-remote-test-case-ancestors-get | Walk prerequisite chains |
muggle-remote-test-case-bulk-preview-submit | Async batch preview (~50% cheaper) |
muggle-remote-test-plan-graph-rebuild | Rebuild the prerequisite graph |
Bulk-preview submissions return a jobId immediately. Poll muggle-remote-bulk-preview-job-get until terminal, then persist with the matching -create tool. -list and -cancel round out the set.
| Scripts and workflows | Purpose |
|---|---|
muggle-remote-test-script-list / -get / -delete | Manage test scripts |
muggle-remote-action-script-get / -delete | Manage recorded action scripts |
muggle-remote-workflow-start-website-scan | Scan a site for use cases |
muggle-remote-workflow-start-test-case-detection | Generate test cases |
muggle-remote-workflow-start-test-script-generation | Generate a script |
muggle-remote-workflow-start-test-script-generation-bulk | Generate in bulk |
muggle-remote-workflow-start-test-script-replay | Replay one script |
muggle-remote-workflow-start-test-script-replay-bulk | Batch replay |
muggle-remote-workflow-cancel-run / -cancel-runtime | Cancel in flight |
muggle-remote-wf-get-* | Poll the latest run of each workflow type |
| Local execution | Purpose |
|---|---|
muggle-local-check-status | Browser runner status |
muggle-local-execute-test-generation | Generate a script by driving the browser |
muggle-local-execute-replay | Replay an existing script |
muggle-local-cancel-execution | Cancel the active run |
muggle-local-run-result-list / -get | Results, screenshots, and cloud refs (viewUrl) |
muggle-local-run-steps-get | A run's ordered steps beside the frame each produced |
muggle-local-test-script-list / -get | Read locally cached scripts |
muggle-local-last-host-* / -last-project-* | Remember the host and project between runs |
muggle-local-preferences-set | Set harness preferences |
muggle-remote-local-run-upload | Publish a local run to the cloud |
Reporting — muggle-remote-report-stats-summary-get, -cost-query, -final-generate (PDF/HTML/Markdown), -preferences-upsert.
Administration — muggle-remote-prd-file-* (upload and process requirements docs), muggle-remote-secret-* (credentials for test environments), muggle-remote-wallet-* (credits, payment methods, auto-topup), muggle-remote-recommend-cicd-setup / -recommend-schedule, muggle-remote-user-feedback-*.
---
```bash
unauthorized_client during login — the MCP server is pointed at one environment and you're authenticating against another. Fix MUGGLE_MCP_PROMPT_SERVICE_TARGET and restart the client.
Browser runner not found
muggle setup --force
muggle doctor
Authentication keeps expiring
muggle logout
rm ~/.muggle-ai/oauth-session.json ~/.muggle-ai/api-key.json
muggle login
---
muggle-ai-works 是一个强大的 AI 驱动工具,旨在让各类 AI coding agent 具备执行真实浏览器 E2E(端到端)验收测试的能力。通过该工具,开发者可以用纯英文描述测试需求,由 AI 自动生成测试脚本并在 localhost 上进行回放。它支持捕获截图并验证诸如注册、结账、仪表盘等关键用户流程。无论你使用的是 Claude Code、Cursor、Codex 还是 Windsurf,都能通过一次安装赋予 AI 像真实用户一样操作应用的能力。
本项目核心功能在于通过 AI 实现自动化测试闭环。对于 Claude Code 用户,你可以直接使用 `/muggle:muggle-test-feature-local` 命令,用自然语言描述测试目标,AI 会自动定位项目、创建测试用例并启动真实浏览器进行验证,最后通过截图报告结果。对于 Cursor、Codex、Windsurf 等支持 MCP 的客户端,你可以直接调用本地执行的 MCP tools(如 `muggle-local-execute-test-script-replay`)来实现类似的自动化测试流程。
运行本项目需要安装 Python 3.10 或更高版本,并且需要预先安装 skill-creator 插件。在进行评估或运行特定脚本时,请确保已配置好相应的插件路径及模型权限(如 Claude Opus)。
安装过程取决于你使用的客户端。对于 Claude Code 用户,可以获得完整的插件体验,通过运行 `/plugin marketplace add` 指令添加仓库地址,并使用 `/plugin install muggleai@muggle-works` 进行安装。安装完成后,你将获得包括 `/muggle:muggle` 命令路由、`/muggle:muggle-do` 自动化开发流水线以及 `/muggle:muggle-test` 驱动型 E2E 验收测试在内的全套工具集。对于其他 MCP 客户端,则需根据其 MCP 协议进行集成。
快速上手指南:在 Claude Code 中,你可以直接通过指令驱动 AI 完成开发任务。例如,使用 `/muggle:muggle-do "Add a logout button to the header"`,AI 将自动执行从需求理解、编写代码、运行单元测试到启动真实浏览器进行 E2E 验收测试的全流程,并最终提交包含测试结果的 PR。对于其他 MCP 客户端,建议参考直接调用 MCP 工具的工作流进行操作。
本项目提供 CLI 命令行参考,开发者可以通过命令行界面直接调用相关的测试与开发指令。对于集成开发者,可以通过调用 `muggle-*` 系列 MCP 工具来实现与 AI Agent 的深度交互。
项目包含两个核心工作流模块:1. `/muggle:muggle-test-feature-local`:用于本地功能测试,通过自然语言描述需求,AI 自动执行浏览器回放并反馈结果;2. `/muggle:muggle-do`:全自动开发流水线,实现从需求描述到提交 PR 的闭环,涵盖代码编写、单元测试及基于真实浏览器的 E2E 验收测试,极大提升了开发效率。
高质量的AI驱动的Web测试工具
该工具未明确声明开源协议,商业使用前请联系原作者确认授权范围,避免侵权风险。
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。
经综合评估,MCP工具 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 | muggle-ai-works |
| 原始描述 | 开源MCP工具:Your AI coding agent writes code fast — we make sure the web product actually wo。⭐16 · TypeScript |
| Topics | ai-agentsai-powered-testingbrowser-automation |
| GitHub | https://github.com/multiplex-ai/muggle-ai-works |
| 语言 | TypeScript |
收录时间:2026-06-24 · 更新时间:2026-06-26 · License:未公布 · 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