MCP 助手
- 作者仓库星标 47,548
- 作者仓库 metabase
Browser Automation with Playwright MCP (Metabase)
A Playwright MCP server is configured in .mcp.json. Load the tool schemas first with ToolSearch: select:mcp__playwright__browser_navigate,mcp__playwright__browser_snapshot,mcp__playwright__browser_click,mcp__playwright__browser_fill,mcp__playwright__browser_type,mcp__playwright__browser_press_key,mcp__playwright__browser_hover,mcp__playwright__browser_take_screenshot,mcp__playwright__browser_close
If ToolSearch says "MCP servers still connecting," wait a few seconds and retry — the server takes a moment to start on first use.
Core pattern: Snapshot → Act → Check
browser_snapshot— see what's on screen, get element refs- Act —
browser_click,browser_fill,browser_type, etc. using refs from the snapshot - Check the inline response — every action returns a snapshot in its response. Read it.
When to take a separate browser_snapshot after acting:
- The inline response snapshot looks wrong, empty, or unchanged — take a fresh one (async rendering may not have completed)
- You need refs for your NEXT action — the inline snapshot's refs are valid, use them directly
- You're unsure if the action worked — take one more snapshot to confirm
When you do NOT need a separate snapshot after acting:
- The inline response already shows the expected change (e.g., you clicked a link and the response shows the new page)
- You're about to take a screenshot anyway (
browser_take_screenshotshows the current state) - You're doing a chain of actions on the same form (e.g., filling multiple fields) — snapshot once at the end, not after each fill
Element refs go stale after every action. Use refs from the most recent snapshot or inline response — never from an earlier one.
How to interact with Metabase's UI components
Metabase uses Mantine UI components. Most interactions work with a plain browser_click. The hover-before-click pattern is only needed for specific component types.
Regular buttons, links, form inputs, checkboxes, tabs:
Just browser_click them directly. No hover needed.
Buttons that open dropdown menus (e.g., "+ New", "..." action menus, filter type pickers):
These use Mantine's <Menu> component which has a race condition with direct clicks. Hover before clicking these:
browser_hoveron the buttonbrowser_clickon the button- Check the inline response — if the menu appeared, use its refs directly
How to tell if a button opens a dropdown menu: it usually has a chevron/arrow icon, a "..." label, or is labeled as creating something new (like "+ New"). If unsure, try a direct click first — if it doesn't work, retry with hover.
Select and dropdown components (e.g., database picker, column picker):
Mantine Select/MultiSelect are NOT native <select> elements. browser_select_option will NOT work. Instead:
browser_clickon the input/triggerbrowser_clickon the option you want (use refs from the inline response)
You can also type into the input to filter options before clicking.
Modals and dialogs:
To dismiss: browser_click the close/action button, or browser_press_key with Escape.
⚠️ Mantine Escape-inside-modal trap: Pressing Escape while focus is inside a Mantine popover/Select/MultiSelect that is itself nested in a modal closes the entire modal and discards every form field you've already filled. To dismiss just an open dropdown, prefer browser_click outside the dropdown (or click another field). Only press Escape when you actually want the whole modal gone.
Mantine portals + scoped snapshots: Mantine renders dropdowns, popovers, and tooltips into a portal at <body> level — they are NOT children of the [role=dialog] element. If you scope browser_snapshot to the modal, dropdown options will be missing. Take a full-page snapshot when interacting with portaled content.
Login
browser_navigatetohttp://localhost:$MB_JETTY_PORT/auth/loginbrowser_snapshot→browser_fillemail and password →browser_clicksign-in buttonbrowser_navigatetohttp://localhost:$MB_JETTY_PORT/— always navigate explicitly to the home page after login. Do NOT rely on the login redirect alone. The redirect can leave the browser session in a state where clicks don't register.browser_snapshotto confirm you're logged in
Quick login via API (alternative)
Get a session token via API and set it as a cookie — faster than filling the login form:
./bin/mage -bot-api-call /api/session --method POST --body '{"username":"<email>","password":"<password>"}'Extract the id from the response, then use browser_evaluate with script:
document.cookie = 'metabase.SESSION=<token>;path=/'Then browser_navigate to the target page. Use the credentials from ./bin/mage -bot-server-info.
When clicks don't work
- Take a fresh snapshot (async rendering). 2. Try hover + click (menu triggers). 3. Try keyboard (focus + Enter). 4. After 3 attempts, report and move on.
Rules
- Always use
http://localhost:$MB_JETTY_PORT - Close the browser when done
- Use inline response snapshots when sufficient — only take separate
browser_snapshotwhen needed - Browser is pre-configured: 1440x900 viewport, full snapshot mode, isolated session, 10s action timeout
- 流狐分类
- AI 智能
- 作者声明 Agent
- 未找到明确声明；不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描，不代表运行安全
- 作者 / 版本 / 许可
- @metabase · 未声明 license
- 流狐 Token 估算
- 低消耗
- 流狐接入估算
- 即装即用
- 是否需要外部 API Key
- 未发现要求
- 检测到的系统要求
- 未声明
- 底层运行要求
- 未声明
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 检测到的网络行为
- 仅限本地
- 安装命令数
- 无（仅作为资料）
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
作者没有在当前 SKILL.md 中定义固定输出样例。browsersnapshot — see what's on screen, get element refs Act — browserclick, browserfill, browsertype, etc. using refs from the snapshot Check the inline response — every action returns a snapshot in its response. Read it.
Metabase uses Mantine UI components. Most interactions work with a plain browserclick. The hover-before-click pattern is only needed for specific component types. Regular buttons, links, form inputs, checkboxes, tabs: Just browserclick them directly. No hover…
browsernavigate to http://localhost:$MBJETTYPORT/auth/login browsersnapshot → browserfill email and password → browserclick sign-in button browsernavigate to http://localhost:$MBJETTYPORT/ — always navigate explicitly to the home page after login. Do NOT rely…
Get a session token via API and set it as a cookie — faster than filling the login form: Extract the id from the response, then use browserevaluate with script: Then browsernavigate to the target page. Use the credentials from ./bin/mage -bot-server-info.
Take a fresh snapshot (async rendering). 2. Try hover + click (menu triggers). 3. Try keyboard (focus + Enter). 4. After 3 attempts, report and move on.
Always use http://localhost:$MBJETTYPORT Close the browser when done Use inline response snapshots when sufficient — only take separate browsersnapshot when needed
# Browser Automation with Playwright MCP (Metabase)
A Playwright MCP server is configured in `.mcp.json`. Load the tool schemas first with `ToolSearch`: `select:mcp__playwright__browser_navigate,mcp__playwright__browser_snapshot,mcp__playwright__browser_click,mcp__playwright__browser_fill,mcp__playwright__browser_type,mcp__playwright__browser_press_key,mcp__playwright__browser_hover,mcp__playwright__browser_take_screenshot,mcp__playwright__browser_close`
If ToolSearch says "MCP servers still connecting," wait a few seconds and retry — the server takes a moment to start on first use.
## Core pattern: Snapshot → Act → Check
1. **`browser_snapshot`** — see what's on screen, get element refs
2. **Act** — `browser_click`, `browser_fill`, `browser_type`, etc. using refs from the snapshot
3. **Check the inline response** — every action returns a snapshot in its response. Read it.
**When to take a separate `browser_snapshot` after acting:**
- The inline response snapshot looks wrong, empty, or unchanged — take a fresh one (async rendering may not have completed)
- You need refs for your NEXT action — the inline snapshot's refs are valid, use them directly
- You're unsure if the action worked — take one more snapshot to confirm
**When you do NOT need a separate snapshot after acting:**
- The inline response already shows the expected change (e.g., you clicked a link and the response shows the new page)
- You're about to take a screenshot anyway (`browser_take_screenshot` shows the current state)
- You're doing a chain of actions on the same form (e.g., filling multiple fields) — snapshot once at the end, not after each fill
**Element refs go stale after every action.** Use refs from the most recent snapshot or inline response — never from an earlier one.
…作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。
章节 -> Core pattern: Snapshot → Act → Check → How to interact with Metabase's UI components → Login → Quick login via API (alternative) → When clicks don't work → Rules
要点 -> browsersnapshot · Act · Check the inline response · When to take a separate browsersnapshot after acting · When you do NOT need a separate snapshot after acting · Element refs go stale after every action. · Regular buttons, links, form inputs, checkboxes, tabs · Hover before clicking
文件/命令 -> .mcp.json · ToolSearch · browsersnapshot · browserclick · browserfill · browsertype · browsertakescreenshot · <Menu>
内容 SHA-256 -> 706df07222c1
原文结构
适用与边界
原文中的明确线索
.mcp.json、ToolSearch、browsersnapshot、browserclick、browserfill、browsertype、browsertakescreenshot、<Menu>