- The OAUTH from ngrok could not be handled by OpenAI and was
only haölf implemented. The policy file is the right way but it still
wont detect it..
- Most importantly we trail the logs at the end of the script to
avoid the script from terminating.
Features:
- Add tmux_server.py with full session management capabilities
- Convert TheCoder script from screen to tmux with HOME bind mount fix
- Add enabled flag to MCPServerConfig for selective server startup
- Tmux now default, screen legacy (disabled by default)
- Update documentation and architecture to reflect tmux preference
Session Management:
- create_session, execute, peek, list_sessions, kill_session
- attach_session and share_session with multi-user instructions
- Better multi-user support than screen with native tmux capabilities
Testing:
- Add test_tmux_session.py for comprehensive tmux functionality testing
- Add test_screen_utf8.py for UTF-8 handling
- Add MCP_QUICK_REFERENCE.md for AI handoff documentation
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
**Fixed Issues**:
- Proper config file loading from ~/.claude/mcp-browser/config.yaml
- Correct MCPBrowser initialization with config_path parameter
- Fixed server config attribute access using getattr()
- Updated runtime status detection logic
- Reduced initialization wait time for better performance
**Working Features**:
- ✅ Discovers 27 tools from 4 built-in servers (screen, memory, patterns, onboarding)
- ✅ Loads 7 configured external servers from config file
- ✅ Generates comprehensive JSON documentation with runtime status
- ✅ Includes server PIDs and active status for monitoring
- ✅ All regex JSONPath queries working ($.tools[?(@.name =~ /pattern/i)])
The gen_apidoc command now provides complete MCP API documentation
suitable for adding to AI project knowledge bases.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
**Enhanced JSONPath Support**:
- Manual regex implementation for queries like `$.tools[?(@.name =~ /pattern/i)]`
- Supports case-insensitive searches with /i flag
- Works on both tool names and descriptions
- Fallback to standard JSONPath for non-regex queries
**gen_apidoc Command**:
- New `python setup.py gen_apidoc` command
- Generates comprehensive JSON documentation of MCP API
- Includes all servers, tools, schemas, and capabilities
- AI-optimized format with discovery patterns
- Runtime server status information
- Perfect for adding to project knowledge bases
**API Documentation Features**:
- Complete server inventory with tool counts
- Capability inference from tool names/descriptions
- Discovery pattern examples for common queries
- Sparse mode information for context optimization
- Tool grouping by server with metadata
This enables powerful regex-based tool discovery and provides
comprehensive API documentation for AI consumption.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
**Onboarding Enhancements**:
- Added explicit server discovery examples
- Included Claude Code server usage patterns
- Added read_file tool call examples with proper namespacing
**Xilope Production Guide**:
- Complete production environment documentation
- Memory storage integration details (/mnt/data/claude/claude/.mcp-memory/)
- cmem wrapper integration (~/bin/cmem → /usr/local/bin/cmem)
- Bidirectional sync workflows and best practices
**Server Updates**:
- Enhanced onboarding server to serve predefined markdown files
- Priority: predefined files → default.md → fallback instructions
This provides comprehensive guidance for both general MCP Browser usage
and Xilope's specific production environment with cmem integration.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major enhancements to MCP Browser functionality:
**Interactive Client & Testing**:
- New comprehensive interactive client with readline support
- Tab completion for commands and tools
- Enhanced tool testing with sample argument generation
- Standalone executable script for easy testing
**cmem Integration**:
- Bidirectional sync between memory server and cmem
- Identity-specific memory contexts
- Automatic task, pattern, and decision synchronization
- Graceful degradation when cmem unavailable
**Developer Experience**:
- Updated tool descriptions with clear proxy pattern explanations
- Comprehensive handoff documentation for AI assistant transitions
- 32 new tests covering all enhanced functionality
- All tests passing (46 passed, 3 skipped)
**Context Optimization**:
- Maintained sparse mode efficiency
- Clear meta-tool descriptions with emojis
- Enhanced onboarding guide with practical examples
This update significantly improves both AI assistant workflow continuity
and developer testing capabilities while maintaining the project's core
principle of context efficiency.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add 'make run' target that installs and restarts daemon from home directory
- Add 'make restart' target to stop and start daemon without install
- Add 'make stop' target to safely stop running daemon
- Add 'make status' target to check daemon status with PID verification
- Fixes issue where daemon doesn't update after 'make install'
- Ensures daemon runs from .venv/bin/ to avoid stale system-wide version
- Includes process verification with ps command to confirm replacement
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add enable_multiuser tool to enable multiuser mode on sessions
- Add attach_multiuser tool to provide attach instructions
- Add add_user tool for access control list management
- Peek functionality works seamlessly with multiuser sessions
- Create comprehensive test for multiuser functionality
- All existing functionality preserved and tested
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Read screen hardcopy output as binary first
- Decode with UTF-8 using 'replace' error handling
- Fallback to latin-1 encoding if needed
- Strip ANSI escape sequences from output
- Handles mixed encodings and binary data gracefully
This fixes crashes when screen sessions contain non-UTF-8 bytes
or terminal control sequences.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add inotify-based config file watching for runtime server updates
- Include external server information in mcp_discover results
- Add comprehensive default onboarding explaining proxy architecture
- Update sparse tool description to show server count
- Config changes are now automatically detected and reloaded
- No restart required when adding new MCP servers to config.yaml
The onboarding now fully explains:
- Proxy mode connecting to external MCP servers
- Built-in tools always available
- Discovery examples for finding servers and tools
- Runtime configuration without restarts
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Remove unused imports (signal, yaml, os, socket, ConfigLoader)
- Remove unused variable assignments in argument parsers
- Update integration test to send initialize request first
- Fix test to match new server mode behavior
All unit tests pass, integration test needs initialize handshake.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix protocol version mismatch (0.1.0 -> 2024-11-05)
- Fix server mode blocking on startup causing Claude Desktop timeout
- Add --version flag to show version information
- Implement proper daemon cleanup when starting new daemon
- Add kill_daemon_with_children() to properly terminate process tree
- Fix dictionary iteration error during shutdown
- Ensure sparse mode is always enabled (3 tools only)
- Fix async stdin reading in base server to prevent EOF loops
- Add syslog support for server mode logging
- Switch from stdin.read() to readline() for proper JSON-RPC handling
- Add comprehensive MCP protocol test suite
The tool now works correctly as an MCP proxy between Claude Desktop
and MCP servers with additional built-in tools.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
The server was hanging on initialize requests because:
1. It was calling browser.initialize() at startup which tried to connect to upstream servers
2. It was using blocking stdin.read(4096) instead of line-based reading
Fixed by:
- Removing premature initialization in server mode (let it happen lazily)
- Switching to readline() for proper line-based JSON-RPC handling
- Adding proper error responses for malformed JSON
This resolves the 60-second timeout error when Claude Desktop tries to connect.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fixed ValueError with closed file when daemonizing
- Properly handle file descriptors with dup2
- Move signal handlers inside async context
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Major refactoring to fix high CPU usage and improve architecture:
## Fixed Issues
- MCP servers were stuck in infinite loops when stdin closed
- Fixed by checking for EOF (empty string) from stdin.read()
- Fixed indentation error in base.py causing syntax errors
## New Architecture
- Split into separate client and daemon binaries:
- `mcp-browser`: Smart client that can use daemon or run standalone
- `mcp-browser-daemon`: Persistent daemon process
- `mcp-browser-legacy`: Old monolithic version (deprecated)
## Client Features
- Auto-detects and uses daemon if available
- Can auto-start daemon if needed
- Falls back to standalone mode
- Supports `--use-daemon` with modes: auto, always, never
- Works as MCP server (stdin/stdout) or CLI tool
## Daemon Features
- Runs as background process with socket server
- Supports multiple concurrent clients
- Can run in foreground with `--foreground`
- Includes systemd service files for production
- Proper signal handling and cleanup
## Usage Examples
```bash
# CLI usage (auto-uses daemon if available)
mcp-browser tools-list
mcp-browser tools-call builtin:patterns::list_patterns '{}'
# Force standalone mode
mcp-browser --use-daemon never tools-list
# Run daemon manually
mcp-browser-daemon --foreground --log-level DEBUG
# Use as MCP server
echo '{"method":"tools/list"}' | mcp-browser --mode server
```
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added parents=True to mkdir call to create parent directories
- Fixes FileNotFoundError when starting daemon in background
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added proper package discovery for mcp_servers modules
- Created __init__.py files for all mcp_servers subpackages
- Added MANIFEST.in to ensure all files are included in distribution
- Removed mcp-browser-demo entry point from setup.py
- Fixed package_data to include all necessary files
The mcp_servers modules are now properly installed alongside mcp_browser,
allowing built-in servers to work correctly after installation.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added comprehensive logging system with configurable levels
- TRACE: Shows raw JSON-RPC I/O with server names
- DEBUG: Detailed operational logging
- INFO/WARNING/ERROR: Standard logging levels
- New command line options:
- --log-level: Set logging level (TRACE/DEBUG/INFO/WARNING/ERROR)
- --log-file: Log to file instead of stderr
- Improved error handling and timeouts:
- Initial server discovery timeout reduced to 3 seconds
- Servers marked as offline for 30 minutes after failure
- Better error messages with server context
- All debug output now goes to stderr, keeping stdout clean for JSON
Example usage:
mcp-browser --log-level TRACE tools-list # See raw I/O
mcp-browser --debug --log-file debug.log # Debug to file
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Implement socket-based daemon mode using Unix domain sockets
- Allows multiple clients to connect to a single MCP Browser instance
- Supports automatic daemon detection and connection
- Added --daemon-start, --daemon-stop, --daemon-status commands
- Improve debug output handling
- All debug output now goes to stderr instead of stdout
- Added debug_print() and debug_json() utilities
- Debug messages show before and after server communication
- Fix builtin-only mode handling
- Properly route tools/list and tools/call when no external server
- Apply sparse mode filtering to builtin server tools
- Improve JSON-RPC command output
- Raw jsonrpc command now outputs proper JSON for piping
- Other commands use human-friendly formatting
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Created comprehensive default configuration system
- Config directory at ~/.claude/mcp-browser/ with:
- config.yaml with example MCP server configurations
- onboarding.md with detailed usage documentation
- patterns/ directory for system and custom patterns
- logs/ and backups/ directories
- Added checksum system to detect unmodified config files
- Enhanced CLI with new options:
- --list-servers to show available servers
- --show-config to display configuration
- --test to test server connections
- --debug for detailed output
- Improved help text with examples and better documentation
- Updated ConfigLoader to use new config directory structure
- First run automatically creates default configuration
The system now provides a user-friendly experience similar to
claude-composer with proper configuration management.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fixed NameError by adding missing Union import in filter.py
- Reorganized all tests into tests/ subdirectory
- Fixed recursive initialization issue in proxy.py
- Added proper test infrastructure with Makefile and setup.py test target
- Created test_config.yaml for test configurations
- Added Brave Search integration test (requires BRAVE_API_KEY)
- Fixed async test fixtures to use @pytest_asyncio.fixture
- Updated tests to handle 3 sparse tools (including onboarding)
- Fixed JSONPath queries to avoid unsupported filter syntax
- Created unit tests that don't require server initialization
- Added test_simple.py for basic functionality tests
All unit tests now pass successfully. Integration tests that require
full server setup are marked as skipped.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Change license to GPLv3+ (OSI approved)
- Update repository URL to github.com/Xilope0/mcp-browser
- Set correct author as Claude4Ξlope <xilope@esus.name>
- Add installation instructions and badges to README
- Add contributing section highlighting AI-only development
- Update all metadata consistently across files
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude4Ξlope <xilope@esus.name>
- Use temporary YAML config file to specify claude MCP server
- Update to work with current MCPBrowser API
- Add better error handling and cleanup
- Test sparse mode and tool discovery
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Enhanced setup.py with AI-friendly documentation generation
- Added 'python setup.py aidocs' command for:
- Automatic API documentation via pydoc
- ctags generation for code navigation
- Project structure documentation
- API summary generation
- Added CLAUDE.md explaining AI-only development
- Created __main__.py for command-line interface
- Added test_claude_connection.py to verify claude-code integration
- Added py.typed for type checking support
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
esus
Andre Heinecke
gpt-5-codex
Claude4Ξlope