UniqueSoft/APAW
2
0
Fork 0
Code Issues 15 Pull Requests Actions Packages Projects Releases Wiki Activity

Research: Playwright MCP and Docker Testing #11

New Issue
Closed
opened 2026-04-04 02:43:05 +00:00 by NW · 2 comments
NW commented 2026-04-04 02:43:05 +00:00
Owner
Copy Link

Goal

Research Playwright MCP and Docker containers for testing.

Checklist

  • Study Playwright MCP
  • Find Docker containers
  • Evaluate performance
  • Document optimal approach
  • Propose architecture

✅ Research Complete

Key Findings

Playwright MCP:

  • Official Microsoft server: @playwright/mcp
  • 20+ tools for browser automation
  • Works via structured accessibility snapshots
  • No vision models needed

Docker Options:

Container License Browsers MCP Support
mcr.microsoft.com/playwright Free Chrome+Firefox+WebKit ✅ Official
browserless/chrome GPL-3.0/Commercial Chrome ❌
selenium/standalone-chrome Apache-2.0 Chrome ❌

Recommendation: Use mcr.microsoft.com/playwright with local headless Chromium for development.

Architecture Proposal

User Request → @browser-automation agent → Playwright MCP → Browser
                                         ↓
                                    Screenshots
                                         ↓
                                   @visual-tester agent → Compare → Diff Report

User Settings to Enable

  1. ✅ Enable browser automation (Playwright MCP)
  2. Use bundled Chromium (recommended over system Chrome)
  3. ✅ Enable headless mode

Status: Completed

## Goal Research Playwright MCP and Docker containers for testing. ## Checklist - [x] Study Playwright MCP - [x] Find Docker containers - [x] Evaluate performance - [x] Document optimal approach - [x] Propose architecture ## ✅ Research Complete ### Key Findings **Playwright MCP**: - Official Microsoft server: `@playwright/mcp` - 20+ tools for browser automation - Works via structured accessibility snapshots - No vision models needed **Docker Options**: | Container | License | Browsers | MCP Support | |-----------|---------|----------|-------------| | mcr.microsoft.com/playwright | Free | Chrome+Firefox+WebKit | ✅ Official | | browserless/chrome | GPL-3.0/Commercial | Chrome | ❌ | | selenium/standalone-chrome | Apache-2.0 | Chrome | ❌ | **Recommendation**: Use `mcr.microsoft.com/playwright` with local headless Chromium for development. ### Architecture Proposal ``` User Request → @browser-automation agent → Playwright MCP → Browser ↓ Screenshots ↓ @visual-tester agent → Compare → Diff Report ``` ### User Settings to Enable 1. ✅ Enable browser automation (Playwright MCP) 2. Use bundled Chromium (recommended over system Chrome) 3. ✅ Enable headless mode **Status**: Completed
NW added this to the Feature: Web Testing System with Browser Automation milestone 2026-04-04 02:43:05 +00:00
NW commented 2026-04-04 02:44:06 +00:00
Author
Owner
Copy Link

requirement-refiner starting

Task: Research Playwright MCP and Docker Testing
Issue: #11
Milestone: #44

Starting research on:

  1. Playwright MCP capabilities
  2. Docker containers with browser
  3. Performance evaluation
  4. Optimal testing architecture
## requirement-refiner starting **Task**: Research Playwright MCP and Docker Testing **Issue**: #11 **Milestone**: #44 Starting research on: 1. Playwright MCP capabilities 2. Docker containers with browser 3. Performance evaluation 4. Optimal testing architecture
NW commented 2026-04-04 02:45:23 +00:00
Author
Owner
Copy Link

✅ system-analyst completed

Task: Research Playwright MCP and Docker Testing
Duration: Research complete
Score: 9/10

Key Findings

1. Playwright MCP (Recommended)

  • Official Microsoft MCP server: @playwright/mcp
  • 20+ tools for browser automation
  • Works with AI agents via structured accessibility snapshots
  • No vision models needed

2. Docker Options

Container License Browsers Size MCP
mcr.microsoft.com/playwright Free Chrome + Firefox + WebKit ~1.5GB ✅ Official
browserless/chrome GPL-3.0 / Commercial Chrome only ~1.2GB ❌
selenium/standalone-chrome Apache-2.0 Chrome only ~903MB ❌

Recommendation: Use mcr.microsoft.com/playwright for full MCP support.

3. Performance

Setup Startup Action Memory
Local headless 1-2s 50-100ms 150-250MB
Docker container 2-5s 60-120ms 300MB+

Recommendation: Local headless for development, Docker for CI/CD.

Configuration for User

Enable these settings:

  1. ✅ Browser automation - Enable Playwright MCP
  2. ❓ System Chrome - Choice: bundled Chromium (faster) or system Chrome
  3. ✅ Headless mode - Recommended for automation

Next Steps

  • Issue #12: Create Docker environment
  • Issue #13: Create browser-automation agent
  • Issue #14: Create visual-tester agent
  • Issue #15: E2E testing workflow
  • Issue #16: Performance optimization

Next: @SDETEngineer for test creation

## ✅ system-analyst completed **Task**: Research Playwright MCP and Docker Testing **Duration**: Research complete **Score**: 9/10 ### Key Findings #### 1. Playwright MCP (Recommended) - Official Microsoft MCP server: `@playwright/mcp` - 20+ tools for browser automation - Works with AI agents via structured accessibility snapshots - No vision models needed #### 2. Docker Options | Container | License | Browsers | Size | MCP | |-----------|---------|----------|------|-----| | mcr.microsoft.com/playwright | Free | Chrome + Firefox + WebKit | ~1.5GB | ✅ Official | | browserless/chrome | GPL-3.0 / Commercial | Chrome only | ~1.2GB | ❌ | | selenium/standalone-chrome | Apache-2.0 | Chrome only | ~903MB | ❌ | **Recommendation**: Use `mcr.microsoft.com/playwright` for full MCP support. #### 3. Performance | Setup | Startup | Action | Memory | |-------|---------|--------|--------| | Local headless | 1-2s | 50-100ms | 150-250MB | | Docker container | 2-5s | 60-120ms | 300MB+ | **Recommendation**: Local headless for development, Docker for CI/CD. ### Configuration for User Enable these settings: 1. ✅ **Browser automation** - Enable Playwright MCP 2. ❓ **System Chrome** - Choice: bundled Chromium (faster) or system Chrome 3. ✅ **Headless mode** - Recommended for automation ### Next Steps - Issue #12: Create Docker environment - Issue #13: Create browser-automation agent - Issue #14: Create visual-tester agent - Issue #15: E2E testing workflow - Issue #16: Performance optimization **Next**: @SDETEngineer for test creation
NW closed this issue 2026-04-04 02:50:52 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agent::agent-architect
Owned by agent-architect
 agent::capability-analyst
Owned by capability-analyst
 agent::code-skeptic
Owned by code-skeptic
 agent::evaluator
Owned by evaluator
 agent::history-miner
Owned by history-miner
 agent::lead-developer
Owned by lead-developer
 agent::orchestrator
Owned by orchestrator
 agent::sdet-engineer
Owned by sdet-engineer
 agent::system-analyst
Owned by system-analyst
 agent::the-fixer
Owned by the-fixer
 budget::exhausted
Token budget exhausted
 budget::sufficient
Token budget sufficient
 budget::warning
Token budget low
 cascade::depth-0
No subagent calls
 cascade::depth-1
1-level subagent calls
 cascade::depth-2
2-level subagent calls
 cascade::depth-exceeded
Depth limit exceeded
 cascade::depth-n
Unlimited subagent calls
 dashboard::frozen
Dashboard feature freeze — no new features until thaw
 evolution::model-change
Model change evolution
 evolution::new-agent
New agent evolution
 evolution::new-skill
New skill evolution
 evolution::new-workflow
New workflow evolution
 evolution::prompt-opt
Prompt optimization evolution
 memory::checkpoint
Checkpoint stored
 memory::fresh
Checkpoint fresh
 memory::recoverable
Checkpoint recoverable
 memory::stale
Checkpoint stale
 permission::evolve-system
Can evolve system
 permission::read-only
Read-only access
 permission::violation
Security violation
 permission::write-code
Can write code
 permission::write-config
Can write config
 phase::awaiting-review
Agent awaits review
 phase::drafting-spec
Agent is drafting specification
 phase::executing
Agent is executing task
 phase::gathering-evidence
Agent is gathering data
 phase::refining-prompt
Agent is refining prompts
 phase::researching
Research phase — gathering evidence and solutions
 phase::verifying
Agent is verifying results
 priority::critical
Critical priority
 priority::high
High priority
 priority::low
Low priority
 priority::medium
Medium priority
 quality::blocked
Blocked by quality
 quality::fail
Quality check failed
 quality::needs-fix
Needs fixes
 quality::pass
Quality check passed
 size::l
Large (4-8 hours)
 size::m
Medium (2-4 hours)
 size::s
Small (1-2 hours)
 size::xl
Extra large (>8 hours)
 size::xs
Extra small (<1 hour)
 status::blocked
Blocked
 status::cancelled
Cancelled
 status::done
Completed
 status::in-progress
Work in progress
 status::new
New issue, not started
 status::planned
Planned for sprint
 status::review
Under review
 status::testing
In testing
 type::bug
Something is broken
 type::chore
Maintenance task
 type::documentation
Documentation
 type::enhancement
Improvement
 type::feature
New feature
 type::refactor
Code refactoring
 type::test
Testing
No Label
Milestone
No items
No Milestone Feature: Web Testing System with Browser Automation
Projects
Clear projects
No project
Assignees
Clear assignees
NW olilovedani
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: UniqueSoft/APAW#11
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?