- Block images exceeding 8000px from being included in MCP responses
- Add clear warning messages when images are too large for API
- Always save screenshots to file regardless of size
- Prevents conversation history issues with oversized fullPage screenshots
- Add test script for verifying large image protection
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add browser_set_offline tool documentation
- Document offline parameter in browser_configure tool
- Auto-generated tool documentation now includes all new features
Major enhancements to browser automation and debugging capabilities:
**Console Capture Features:**
- Add console output file option (CLI, env var, session config)
- Enhanced CDP console capture for service worker messages
- Browser-level security warnings and mixed content errors
- Network failure and loading error capture
- All console contexts written to structured log files
- Chrome extension for comprehensive console message interception
**Offline Mode Support:**
- Add browser_set_offline tool for DevTools-equivalent offline mode
- Integrate offline mode into browser_configure tool
- Support for testing network failure scenarios and service worker behavior
**Extension Management:**
- Improved extension installation messaging about session persistence
- Console capture extension with debugger API access
- Clear communication about extension lifecycle to MCP clients
**Technical Implementation:**
- CDP session management across multiple domains (Runtime, Network, Security, Log)
- Service worker context console message interception
- Browser context factory integration for offline mode
- Pure Chromium configuration for optimal extension support
All features provide MCP clients with powerful debugging capabilities
equivalent to Chrome DevTools console and offline functionality.
Implements automatic validation of screenshot dimensions to prevent
"image dimensions exceed max allowed size: 8000 pixels" API errors.
New features:
✅ **Automatic size validation** - Rejects images > 8000px by default
✅ **allowLargeImages flag** - Override validation when needed
✅ **Smart error messages** - Helpful solutions when validation fails
✅ **Image dimension parsing** - Supports PNG and JPEG format detection
✅ **Updated tool description** - Documents size limits and flag usage
Error message provides actionable solutions:
1. Use viewport screenshot (remove fullPage: true)
2. Allow large images (add allowLargeImages: true)
3. Reduce viewport size (browser_configure)
4. Screenshot specific elements (element + ref)
Usage examples:
```json
// Safe viewport screenshot
{"filename": "safe.png"}
// Full page with validation
{"fullPage": true, "filename": "page.png"}
// Override validation for large images
{"fullPage": true, "allowLargeImages": true, "filename": "large.png"}
```
This prevents the frustrating API error: "At least one of the image
dimensions exceed max allowed size: 8000 pixels" by catching oversized
images before they reach the API and providing clear solutions.
Co-Authored-By: Claude <noreply@anthropic.com>
Implements dynamic snapshot configuration that MCP clients can control during
sessions without requiring server restarts or CLI changes.
New tool: browser_configure_snapshots
- Configure includeSnapshots, maxSnapshotTokens, differentialSnapshots at runtime
- Changes take effect immediately for subsequent tool calls
- Shows current settings when called with no parameters
- Provides helpful tips and usage guidance
Key improvements:
1. **Runtime Configuration**: Update snapshot behavior during active sessions
2. **Client Control**: MCP clients can adapt to different workflows dynamically
3. **Immediate Effect**: No server restart required - changes apply instantly
4. **State Tracking**: Context maintains current session configuration
5. **User Friendly**: Clear feedback on current settings and changes
Updated tool descriptions:
- All interactive tools now mention "configurable via browser_configure_snapshots"
- Removed references to CLI-only configuration
- Enhanced browser_snapshot description for explicit snapshots
Benefits for users:
🔄 Dynamic configuration without restarts
🎛️ Client-controlled snapshot behavior
📊 View current settings anytime
⚡ Instant configuration changes
🎯 Adapt settings per workflow/task
Example usage:
```json
{
"includeSnapshots": false,
"maxSnapshotTokens": 25000,
"differentialSnapshots": true
}
```
This transforms snapshot configuration from static CLI options into a flexible
session management system that adapts to client needs in real-time.
Co-Authored-By: Claude <noreply@anthropic.com>
Implements comprehensive solution for browser_click and other interactive tools
returning massive responses (37K+ tokens) due to full page snapshots.
Features implemented:
1. **Snapshot size limits** (--max-snapshot-tokens, default 10k)
- Automatically truncates large snapshots with helpful messages
- Preserves essential info (URL, title, errors) when truncating
- Shows exact token counts and configuration suggestions
2. **Optional snapshots** (--no-snapshots)
- Disables automatic snapshots after interactive operations
- browser_snapshot tool always works for explicit snapshots
- Maintains backward compatibility (snapshots enabled by default)
3. **Differential snapshots** (--differential-snapshots)
- Shows only changes since last snapshot instead of full page
- Tracks URL, title, DOM structure, and console activity
- Significantly reduces token usage for incremental operations
4. **Enhanced tool descriptions**
- All interactive tools now document snapshot behavior
- Clear guidance on when snapshots are included/excluded
- Helpful suggestions for users experiencing token limits
Configuration options:
- CLI: --no-snapshots, --max-snapshot-tokens N, --differential-snapshots
- ENV: PLAYWRIGHT_MCP_INCLUDE_SNAPSHOTS, PLAYWRIGHT_MCP_MAX_SNAPSHOT_TOKENS, etc.
- Config file: includeSnapshots, maxSnapshotTokens, differentialSnapshots
Fixes token overflow errors while providing users full control over
snapshot behavior and response sizes.
Co-Authored-By: Claude <noreply@anthropic.com>
Generated during browser_install_popular_extension testing to verify
Chrome extension functionality works correctly.
Co-Authored-By: Claude <noreply@anthropic.com>
- Add new tool to automatically download and install popular Chrome extensions
- Support for react-devtools, vue-devtools, redux-devtools, and more
- Works around Chrome channel limitations by creating functional demo extensions
- Extensions include proper detection logic and visual indicators
- Auto-generates manifests, content scripts, and popup interfaces
- Registry-based approach for easy extension additions
- Session-specific download directories for isolation
- Updated README with new tool documentation
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
- Add browser_install_extension, browser_list_extensions, browser_uninstall_extension tools
- Support session-based extension isolation between MCP clients
- Extensions loaded via --load-extension Chrome flags at browser startup
- Browser auto-restarts when extensions are added/removed
- Validation ensures extensions only work with Chromium browser
- Warning system for Chrome channel vs pure Chromium compatibility
- Extension management persists across page navigations within session
- Updated README with complete extension tool documentation
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
Add comprehensive artifact storage system with session-specific directories:
- Add --artifact-dir CLI option and PLAYWRIGHT_MCP_ARTIFACT_DIR env var
- Create ArtifactManager class for session-specific artifact organization
- Implement ArtifactManagerRegistry for multi-session support
- Add tool call logging with JSON persistence in tool-calls.json
- Update screenshot, video, and PDF tools to use centralized storage
- Add browser_configure_artifacts tool for per-session control
- Support dynamic enable/disable without server restart
- Maintain backward compatibility when artifact storage not configured
Directory structure: {artifactDir}/{sessionId}/[artifacts, videos/, tool-calls.json]
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add session persistence system to maintain browser contexts across MCP tool calls:
- SessionManager: Global persistent context management keyed by session ID
- BrowserServerBackend: Modified to use session persistence and reuse contexts
- Context: Enhanced to support environment introspection and session ID override
- MCP Roots: Added educational tool descriptions for workspace-aware automation
- Environment Detection: System file introspection for display/GPU/project detection
Key features:
- Browser contexts survive between tool calls preserving cache, cookies, state
- Complete session isolation between different MCP clients
- Zero startup overhead for repeat connections
- Backward compatible with existing implementations
- Support for MCP roots workspace detection and environment adaptation
Tested and verified with real Claude Code client showing successful session
persistence across navigation calls with preserved browser state.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added browser_list_devices tool to show 143+ available device profiles organized by category (iPhone, iPad, Pixel, Galaxy, Desktop, Other)
- Enhanced browser_configure tool with device emulation using Playwright's device descriptors database
- Added support for geolocation coordinates with accuracy settings
- Implemented locale and timezone configuration for internationalization testing
- Added colorScheme preference (light/dark/no-preference) for accessibility testing
- Included permissions management for various browser APIs (geolocation, notifications, camera, microphone)
- Device emulation properly overrides individual viewport/userAgent settings when specified
- All context options are properly applied and browser context is recreated with new settings
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Set browser.isolated = true as default configuration
- Ensures each MCP session gets its own isolated browser context
- Prevents data sharing between different client sessions
- Combined with headed mode for optimal user experience
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Change default headless setting from platform-dependent to false
- Browser now shows GUI windows by default on all platforms
- --headless flag still overrides to enable headless mode when needed
- Provides better user experience with visible browser interactions
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix browser_configure tool to properly use browser context factory
- Remove bypass of browser context factory that was ignoring configuration changes
- Headed mode now works correctly when DISPLAY is available
- Browser windows properly appear when switching from headless to headed mode
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add browser_configure tool to change headless/headed mode, viewport, and user agent during session
- Fix STDIO entry point by preventing stdin close handlers in STDIO mode
- Fix headed mode default behavior when DISPLAY is available on Linux
- Add dynamic browser configuration update mechanism in Context class
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add three new MCP tools for recording browser automation:
- browser_start_recording: Enable video recording with configurable size/filename
- browser_stop_recording: Stop recording and return video file paths
- browser_recording_status: Check recording status and configuration
Key features:
- Automatic video saving when pages/contexts close
- Configurable video size and output directory
- Enhanced LLM guidance with clear workflow instructions
- Integration with existing browser context management
Videos are saved as .webm files in {outputDir}/videos/ directory.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add three new MCP tools for recording browser automation:
- browser_start_recording: Enable video recording with configurable size/filename
- browser_stop_recording: Stop recording and return video file paths
- browser_recording_status: Check recording status and configuration
Key features:
- Automatic video saving when pages/contexts close
- Configurable video size and output directory
- Enhanced LLM guidance with clear workflow instructions
- Integration with existing browser context management
Videos are saved as .webm files in {outputDir}/videos/ directory.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
