playwright · Microsoft

Playwright for AI Agents

Run browser tests, capture screenshots and traces, and automate evidence-backed UI workflows.

Official toolOperational risk: R1R3docs-verified
Agent readiness
86/100
Evidence confidence
docs-verified
Documentation checked
2026-07-10
Independently tested version
Not independently tested

Install for an Agent

Choose an official installation path that matches the runtime. Pin a version for team or CI use, then record the version before the first task.

npmRecommended
macos · linux · windows
$ shell
npm install --save-dev @playwright/test
Authentication and Minimum Permissions
Grant only the permissions the task needs. Pass credentials through environment variables or a platform secret store, never through prompts, repositories, or logs.
No authentication requiredHeadless authentication supported

No service credential is required; restrict filesystem and network access to the task.

Methods
none
Secret environment variables
None
Credential storage
No service credential is stored for this CLI.
Agent and Environment Compatibility
Confirm shell access first, then check the platform, network boundary, and credential path.
claude-codecodexgemini-clicopilot-cli
Environments
local, ci, container, headless
Platforms
macos, linux, windows

Structured Output for Reliable Automation

Prefer a machine-readable format. Treat stdout as the result channel and stderr as diagnostics so the agent can parse failures separately.

json · junit · html · blob
Use --reporter=json or --reporter=junit where supported and keep diagnostic logs on stderr.
--reporter=json--reporter=junit

No independently captured output sample

Structured-output support currently comes from official documentation. CLI Finder does not show a guessed example or invented schema before a bounded, non-destructive execution captures stdout.

R0–R3 Command Risk Guide

Risk is assigned per command. R0 is local or remote read-only, R1 is reversible local write, R2 changes remote state, and R3 can be irreversible or production-impacting.

Read-only does not mean public

R0 only means the command does not change local or remote state. A read-only command may still return secrets, identity data, configuration, or production data. Expose only the minimum needed for the task, and never place it in logs, prompts, or commits.

R0Inspect a test report
Reads an existing report without rerunning browser actions.
$ shell
npx playwright show-report
Idempotent
R1Run browser tests
Executes project-defined browser actions and writes reports and traces.
$ shell
npx playwright test --reporter=json
Confirmation requiredMay repeat a changeSensitive output
R2Record an authenticated flow
Can submit forms or mutate remote state through the browser.
$ shell
npx playwright codegen https://example.com
Confirmation requiredMay repeat a change

How the Agent Readiness Score Is Built

Readiness describes how reliably an agent can operate the tool. It does not make every command safe and it does not replace an independent execution test.

Documentation indicates an agent-readiness score of 86/100. No local execution test has been recorded.

Structured output
Use --reporter=json or --reporter=junit where supported and keep diagnostic logs on stderr.
18/20
x
Headless operation
Official documentation describes a non-interactive authentication or execution path.
14/15
x
Safety controls
CLI Finder separates read commands from commands that require confirmation.
11/15
x
Determinism
Commands use explicit arguments and documented output controls where available.
8/10
x
Authentication
No service credential is required; restrict filesystem and network access to the task.
10/10
x
Documentation
This entry cites official documentation checked on 2026-07-10.
9/10
x
Installation
Official installation paths cover macOS, Linux, and Windows.
8/8
x
Maintenance
An official source repository is linked for release and maintenance review.
6/7
x
Agent artifacts
CLI Finder can generate registry-derived skills and policies; the tool itself was not credited with shipping them.
2/5
x

Generate a Skill or Agent Policy

Choose an agent and safety mode to generate a copyable artifact with installation, allowed commands, approval boundaries, and the evidence limitation.

Generated artifact preview
SKILL.md
---
name: playwright-agent-workflow
description: Use Playwright for browser testing, screenshots, traces with explicit command risk and evidence boundaries.
---

# Playwright agent workflow

Use this skill when the task needs browser testing, screenshots, traces, authenticated UI flows.

## Evidence boundary

- Registry confidence: `docs-verified`
- Documentation checked: `2026-07-10`
- Locally tested version: `not tested`
- Do not describe this CLI as locally verified until its commands have actually been executed in an isolated environment.

## Executed smoke checks

- No local execution record is available.

## Installation

- npm (macos, linux, windows): `npm install --save-dev @playwright/test`

## Authentication

- Methods: none
- Secret environment variables: none
- Minimum permissions: No service credential is required; restrict filesystem and network access to the task.
- Credential storage: No service credential is stored for this CLI.
- Never print, persist, or commit credential values.

## Allowed commands (read-only)

- `npx playwright show-report` — R0: Reads an existing report without rerunning browser actions.

## Commands requiring explicit approval (read-only)

- None recorded.

## Forbidden commands (read-only)

- R1 `npx playwright test --reporter=json` — Executes project-defined browser actions and writes reports and traces.
- R2 `npx playwright codegen https://example.com` — Can submit forms or mutate remote state through the browser.

## Execution rules

1. Mode boundary: R0 exact commands may be used; R1, R2, and R3 commands are forbidden.
2. Confirm the selected account, project, context, database, namespace, or environment before any command.
3. Prefer structured output using `--reporter=json`, `--reporter=junit`.
4. Capture the exact command, exit code, stdout, and stderr separately.
5. A generated prefix policy must prompt unless that exact prefix is explicitly marked suffix-safe; do not infer safety from the executable name.
6. Never broaden credentials or disable safety controls to make a command succeed.

## Official sources

- [Playwright test CLI documentation](https://playwright.dev/docs/test-cli)
- [Playwright test CLI documentation source repository](https://github.com/microsoft/playwright)

CLI vs MCP vs API for This Task

CLI
Use the CLI on a developer machine, in CI, or in a container when the task should reuse existing shell state, credentials, and scripts and remain directly observable.
MCP
Consider MCP when the agent benefits from controlled tool definitions, delegated identity, or centrally governed server-side access.
API
Use the direct API for persistent application integrations, high-volume requests, or event-driven work where starting a process adds unnecessary overhead.
Read the full CLI vs MCP guide

Verification History and Official Evidence

CLI Finder records documentation review separately from real execution. Installation, help, exit codes, and output cannot be called Verified until they were run.

Current evidence boundary
Official documentation was reviewed, but installation, help output, exit codes, headless behavior, and structured output were not executed locally.
Evidence confidence
docs-verified
Independently tested version
Not independently tested
Test environment
Not recorded
Official sources
Open the official material to confirm the current version and command behavior.

Alternatives and Related Paths

Test browser interfaces and extract authorized web content with auditable artifacts.
Scrape or crawl web pages into Markdown and JSON for downstream agent analysis.
Define a small URL scope, choose extraction or browser automation, and preserve each source URL with the result.
Pair Codex with deterministic local tools and add remote CLIs only when the sandbox and approval policy allow the task.
Use Firecrawl for extraction-first content workflows and Playwright for browser behavior, screenshots, tests, and necessary interaction.

Questions About Playwright for AI Agents