Changelog - JinsongRoh/pydoll-mcp GitHub Wiki
All notable changes to PyDoll MCP Server will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
- Firefox browser support
- Enhanced mobile device emulation
- Visual element recognition
- Natural language to automation conversion
- Cloud browser integration
- Advanced form recognition
- GUI configuration tool
- JSON Parsing Error Resolution: Fixed JSON parsing errors that interfered with MCP client communication
- Stdout/Stderr Separation: Changed banner output to stderr for MCP protocol compliance
- Protocol Compatibility: Ensured all stdout output is proper JSON format
- Enhanced Error Handling: Proper JSON-formatted error messages for better client parsing
- Stdout Cleanup: Redirected all non-JSON output to stderr
- JSON Validation: Strict JSON formatting for all client responses
- Encoding Stability: Improved character encoding handling on Korean Windows systems (CP949/EUC-KR)
- Error Recovery: Robust error recovery for encoding-related failures
- Server Startup: Guaranteed server startup regardless of system encoding settings
- International Support: Enhanced support for non-English Windows environments
- Terminal Compatibility: Improved compatibility across various terminal emulators
- Cross-platform Stability: Better handling of international character encodings
- Korean Windows Support: Full support for Korean (cp949) encoding environments
- Code Page Handling: Better handling of various Windows code pages
- Terminal Detection: Enhanced Windows terminal capability detection
- Environment Variables: Improved handling of Windows environment variables
- Locale Support: Better handling of various system locales
- UTF-8 Defaults: Default UTF-8 encoding where supported
- Terminal Detection: Enhanced terminal capability detection
- Stream Handling: Better stdout/stderr separation
- Memory Usage: Reduced memory usage in banner and output handling
- Startup Time: Faster server initialization
- Error Handling: More efficient error message processing
- Logging Performance: Optimized logging mechanisms
- Debugging: Enhanced debug output and error messages
- Logging: Better structured logging
- Documentation: Updated documentation for new features
- Testing: Improved test coverage for new functionality
- Server Stability: Improved server startup and shutdown processes
- Error Recovery: Better error handling and recovery mechanisms
- Performance Optimization: Reduced memory usage and improved response times
-
Korean Windows Environment Fix: Resolved
UnicodeEncodeError
that prevented server startup on Korean Windows systems - Cross-platform Encoding Safety: Added comprehensive encoding detection and fallback mechanisms
- Enhanced Banner Display: Implemented smart banner selection based on terminal encoding capabilities
- UTF-8 Standards Compliance: Improved UTF-8 handling across all supported platforms
- Encoding Detection: Automatic terminal encoding detection with graceful fallbacks
- Multi-tier Banner System: 3-tier banner system (emoji, ASCII art, plain text) for maximum compatibility
- Stream Encoding Configuration: Automatic UTF-8 stream configuration where supported
- Error Recovery: Robust error recovery for encoding-related failures
- Startup Stability: Guaranteed server startup regardless of system encoding settings
- International Support: Enhanced support for non-English Windows environments
- Terminal Compatibility: Improved compatibility across various terminal emulators
- Fallback Mechanisms: Multiple fallback strategies for various encoding scenarios
- Korean Windows Support: Full support for Korean (cp949) encoding environments
- Code Page Handling: Better handling of various Windows code pages
- Terminal Detection: Enhanced Windows terminal capability detection
- Environment Variables: Improved handling of Windows environment variables
- Locale Support: Better handling of various system locales
- Automatic Configuration: Automatic Claude Desktop setup during pip installation
- Smart Detection: Automatic detection of Claude Desktop configuration paths
- Safe Merging: Intelligent merging with existing configurations
- Backup Protection: Automatic backup of existing configurations
-
New Commands:
auto-setup
,setup-claude
,quick-start
- Interactive Guides: Step-by-step setup assistance
- Better Diagnostics: Enhanced testing and status reporting
- Cross-platform: Improved Windows, macOS, and Linux support
- Post-install Hooks: Automatic setup prompts after installation
- Multiple Entry Points: Various ways to access setup functionality
- Better Error Handling: More helpful error messages and recovery suggestions
- Documentation: Updated documentation with new setup methods
- Setup Wizard: Interactive configuration process
- Automatic Validation: Automatic verification of configuration
- Recovery Options: Automatic recovery suggestions for configuration issues
- Status Monitoring: Real-time configuration status checking
- Zero Webdriver Architecture: Based on Chrome DevTools Protocol
- 75+ Automation Tools: Comprehensive browser control
- AI-powered CAPTCHA Bypass: Automatic Cloudflare and reCAPTCHA solving
- Stealth Mode: Advanced bot detection evasion
- Human Behavior Simulation: Natural interaction patterns
- start_browser: Start browser with advanced configuration
- stop_browser: Safe browser termination
- new_tab: Create isolated tabs
- close_tab: Close tabs and release resources
- list_browsers: List browser instances
- list_tabs: Detailed tab information
- set_active_tab: Switch between tabs
- get_browser_status: Comprehensive status reporting
- navigate_to: Intelligent URL navigation
- refresh_page: Page refresh with cache control
- go_back/go_forward: Browser history navigation
- wait_for_page_load: Advanced page readiness detection
- get_current_url: Current page URL
- get_page_source: HTML source extraction
- get_page_title: Title and metadata
- wait_for_network_idle: Network activity monitoring
- set_viewport_size: Responsive testing
- get_page_info: Comprehensive page analysis
- find_element: Find elements with natural language attributes
- click_element: Human-like clicking
- type_text: Realistic text input
- press_key: Advanced keyboard input
- get_element_text: Intelligent text extraction
- get_element_attribute: Attribute value retrieval
- wait_for_element: Smart element waiting
- scroll_to_element: Smooth scrolling
- hover_element: Natural mouse hovering
- select_option: Dropdown handling
- check_element_visibility: Visibility testing
- drag_and_drop: Advanced drag and drop
- double_click: Double-click simulation
- right_click: Context menu interaction
- upload_file: File upload handling
- take_screenshot: Full page capture
- take_element_screenshot: Precise element capture
- generate_pdf: Professional PDF generation
- save_page_content: Complete page archiving
- capture_video: Screen recording
- extract_images: Image extraction and processing
- execute_javascript: Complete JS execution environment
- inject_script_library: External library injection
- create_data_extractor: Custom data extraction
- automate_form_filling: Automatic form completion
- monitor_page_changes: DOM change monitoring
- execute_script_sequence: Conditional script execution
- create_custom_function: Custom function creation
- analyze_performance: Performance analysis
- enable_stealth_mode: Advanced anti-detection
- bypass_cloudflare: Automatic Turnstile solving
- bypass_recaptcha: reCAPTCHA v3 bypass
- simulate_human_behavior: Realistic user patterns
- randomize_fingerprint: Browser fingerprint rotation
- handle_bot_challenges: Common challenge solving
- evade_detection: Comprehensive evasion techniques
- monitor_protection_status: Real-time security analysis
- proxy_rotation: Dynamic IP changing
- user_agent_rotation: User agent randomization
- header_spoofing: Request header manipulation
- timing_randomization: Human-like timing
- network_monitoring: Comprehensive traffic analysis
- intercept_requests: Real-time request modification
- extract_api_responses: Automatic API capture
- modify_headers: Dynamic header injection
- block_resources: Resource blocking for performance
- simulate_network_conditions: Throttling and latency
- get_network_logs: Detailed activity reporting
- monitor_websockets: WebSocket connection tracking
- analyze_performance: Page performance metrics
- cache_management: Browser cache control
- upload_file: Advanced file uploading
- download_file: Progress-tracked downloading
- extract_page_data: Structured data extraction
- export_data: Multi-format data export
- import_configuration: Configuration import/export
- manage_sessions: Session state management
- backup_browser_state: Complete state backup
- restore_browser_state: State restoration
- Asynchronous Architecture: Fast concurrent execution
- Memory Optimization: Efficient resource usage
- Robust Error Handling: Automatic recovery mechanisms
- Cross-platform Support: Windows, macOS, Linux
- CLI Interface: Powerful command-line tools
- Configuration Management: Flexible configuration options
- Logging and Debugging: Comprehensive diagnostic tools
- Testing Framework: Automated test suite
- Comprehensive Documentation: User guides and API reference
- Example Gallery: Real-world use cases
- Troubleshooting Guide: Common issue resolution
- Community Support: GitHub discussions and issues
- Initial public beta testing
- Core functionality implementation complete
- Community feedback collection
- Performance optimization and bug fixes
- Prototype functionality implementation
- Basic browser automation
- MCP protocol integration
- Initial testing and validation
Version | Key Features | Tool Count | Performance Improvement |
---|---|---|---|
1.1.3 | JSON parsing fix, MCP compliance | 75+ | 20% stability improvement |
1.1.2 | Server stability | 75+ | 15% memory savings |
1.1.1 | Encoding compatibility | 75+ | 100% internationalization |
1.1.0 | One-click setup | 75+ | 90% setup time reduction |
1.0.0 | Initial release | 75+ | Base performance |
Platform | Support Start | Current Status | Special Features |
---|---|---|---|
Windows | v1.0.0 | โ Full support | Korean encoding |
macOS | v1.0.0 | โ Full support | Native optimization |
Linux | v1.0.0 | โ Full support | Various distributions |
Browser | Support Start | Current Status | Key Features |
---|---|---|---|
Chrome | v1.0.0 | โ Full support | All features |
Edge | v1.0.0 | โ Full support | All features |
Firefox | Planned | ๐ In development | Expected v1.2.0 |
Check GitHub release notes for more detailed changes! ๐
GitHub Releases |
Roadmap |
Contribute