playwright-mcp-metabase

Name: playwright-mcp-metabase
Author: metabase

AI Community

Repo stars 47,548
Author repo metabase

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Drive Metabase's UI with the Playwright MCP browser tools (mcp__playwright__browser_*). Covers the snapshot/act/check pattern, M…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Core pattern: Snapshot → Act → Check”, “How to interact with Metabase's UI components”, “Login”, “Quick login via API (alternative)”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name playwright-mcp-metabase directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Core pattern: Snapshot → Act → Check / How to interact with Metabase's UI components / Login” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

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_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.

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_hover on the button
browser_click on 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_click on the input/trigger
browser_click on 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.

browser_navigate to http://localhost:$MB_JETTY_PORT/auth/login
browser_snapshot → browser_fill email and password → browser_click sign-in button
browser_navigate to http://localhost:$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_snapshot to confirm you're logged in

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_snapshot when needed
Browser is pre-configured: 1440x900 viewport, full snapshot mode, isolated session, 10s action timeout

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: AI
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @metabase · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Plug-and-play
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview playwright-mcp-metabase.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# 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.

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> 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
terms    -> 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
files/cmd -> .mcp.json · ToolSearch · browsersnapshot · browserclick · browserfill · browsertype · browsertakescreenshot · <Menu>
body sha256 -> 706df07222c1