# Enhanced MCP Memory
> **โก Optimized for Claude Sonnet 4** - This MCP server works best with Claude Sonnet 4 for optimal performance and AI-powered features.
An enhanced MCP (Model Context Protocol) server for intelligent memory and task management, designed for AI assistants and development workflows. Features semantic search, automatic task extraction, knowledge graphs, and comprehensive project management.
## โจ Key Features
### ๐ง Intelligent Memory Management
- **Semantic search** using sentence-transformers for natural language queries
- **Automatic memory classification** with importance scoring
- **Duplicate detection** and content deduplication
- **File path associations** for code-memory relationships
- **Knowledge graph relationships** with automatic similarity detection
### ๐งฌ Sequential Thinking Engine
- **Structured reasoning chains** with 5-stage process (analysis, planning, execution, validation, reflection)
- **Context management** with automatic token optimization
- **Conversation continuity** across sessions with intelligent summarization
- **Real-time token estimation** and compression (30-70% reduction)
- **Auto-extraction** of key points, decisions, and action items
### ๐ Advanced Task Management
- **Auto-task extraction** from conversations and code comments
- **Priority and category management** with validation
- **Status tracking** (pending, in_progress, completed, cancelled)
- **Task-memory relationships** in knowledge graph
- **Project-based organization**
- **Complex task decomposition** into manageable subtasks
### ๐๏ธ Project Convention Learning
- **Automatic environment detection** - OS, shell, tools, and runtime versions
- **Project type recognition** - Node.js, Python, Rust, Go, Java, MCP servers, etc.
- **Command pattern learning** - Extracts npm scripts, Makefile targets, and project commands
- **Tool configuration detection** - IDEs, linters, CI/CD, build tools, and testing frameworks
- **Dependency management** - Package managers, lock files, and installation commands
- **Smart command suggestions** - Corrects user commands based on project conventions
- **Windows-specific optimizations** - Proper path separators and command formats
- **Memory integration** - Stores learned conventions for AI context and future reference
### ๐ Performance Monitoring
- **Performance monitoring** with detailed metrics
- **Health checks** and system diagnostics
- **Automatic cleanup** of old data and duplicates
- **Database optimization** tools
- **Comprehensive logging** and error tracking
- **Token usage analytics** and optimization recommendations
### ๏ฟฝ Enterprise Features
- **Performance monitoring** with detailed metrics
- **Health checks** and system diagnostics
- **Automatic cleanup** of old data and duplicates
- **Database optimization** tools
- **Comprehensive logging** and error tracking
- **Token usage analytics** and optimization recommendations
### ๏ฟฝ๐ Easy Deployment
- **uvx compatible** for one-command installation
- **Zero-configuration** startup with sensible defaults
- **Environment variable** configuration
- **Cross-platform** support (Windows, macOS, Linux)
## ๐๏ธ Project Structure
```
enhanced-mcp-memory/
โโโ mcp_server_enhanced.py # Main MCP server with FastMCP integration
โโโ memory_manager.py # Core memory/task logic and project detection
โโโ sequential_thinking.py # Thinking chains and context optimization
โโโ database.py # Database operations with retry mechanisms
โโโ requirements.txt # Python dependencies
โโโ setup.py # Package configuration
โโโ data/ # SQLite database storage
โโโ logs/ # Application logs
```
## ๐ Quick Start
### Option 1: Using uvx (Recommended)
```bash
# Install and run with uvx
uvx enhanced-mcp-memory
```
### Option 2: Manual Installation
```bash
# Clone and install
git clone https://github.com/cbunting99/enhanced-mcp-memory.git
cd enhanced-mcp-memory
pip install -e .
# Run the server
enhanced-mcp-memory
```
### Option 3: Development Setup
```bash
# Clone repository
git clone https://github.com/cbunting99/enhanced-mcp-memory.git
cd enhanced-mcp-memory
# Install dependencies
pip install -r requirements.txt
# Run directly
python mcp_server_enhanced.py
```
## โ๏ธ MCP Configuration
Add to your MCP client configuration:
### For uvx installation:
```json
{
"mcpServers": {
"memory-manager": {
"command": "uvx",
"args": ["enhanced-mcp-memory"],
"env": {
"LOG_LEVEL": "INFO",
"MAX_MEMORY_ITEMS": "1000",
"ENABLE_AUTO_CLEANUP": "true"
}
}
}
}
```
### For local installation:
```json
{
"mcpServers": {
"memory-manager": {
"command": "python",
"args": ["mcp_server_enhanced.py"],
"cwd": "/path/to/enhanced-mcp-memory",
"env": {
"LOG_LEVEL": "INFO",
"MAX_MEMORY_ITEMS": "1000",
"ENABLE_AUTO_CLEANUP": "true"
}
}
}
}
```
## ๐ ๏ธ Available Tools
### Core Memory Tools
- `get_memory_context(query)` - Get relevant memories and context
- `create_task(title, description, priority, category)` - Create new tasks
- `get_tasks(status, limit)` - Retrieve tasks with filtering
- `get_project_summary()` - Get comprehensive project overview
### Sequential Thinking Tools
- `start_thinking_chain(objective)` - Begin structured reasoning process
- `add_thinking_step(chain_id, stage, title, content, reasoning)` - Add reasoning steps
- `get_thinking_chain(chain_id)` - Retrieve complete thinking chain
- `list_thinking_chains(limit)` - List recent thinking chains
### Context Management Tools
- `create_context_summary(content, key_points, decisions, actions)` - Compress context for token optimization
- `start_new_chat_session(title, objective, continue_from)` - Begin new conversation with optional continuation
- `consolidate_current_session()` - Compress current session for handoff
- `get_optimized_context(max_tokens)` - Get token-optimized context
- `estimate_token_usage(text)` - Estimate token count for planning
### Enterprise Auto-Processing
- `auto_process_conversation(content, interaction_type)` - Extract memories and tasks automatically
- `decompose_task(prompt)` - Break complex tasks into subtasks
### Project Convention Tools
- `auto_learn_project_conventions(project_path)` - Automatically detect and learn project patterns
- `get_project_conventions_summary()` - Get formatted summary of learned conventions
- `suggest_correct_command(user_command)` - Suggest project-appropriate command corrections
- `remember_project_pattern(pattern_type, pattern, description)` - Manually store project patterns
- `update_memory_context()` - Refresh memory context with latest project conventions
### System Management Tools
- `health_check()` - Check server health and connectivity
- `get_performance_stats()` - Get detailed performance metrics
- `cleanup_old_data(days_old)` - Clean up old memories and tasks
- `optimize_memories()` - Remove duplicates and optimize storage
- `get_database_stats()` - Get comprehensive database statistics
## ๐๏ธ Project Convention Learning
The Enhanced MCP Memory Server automatically learns and remembers project-specific conventions to prevent AI assistants from suggesting incorrect commands or approaches:
### Automatic Detection
- **Operating System**: Windows vs Unix, preferred shell and commands
- **Project Type**: Node.js, Python, Rust, Go, Java, MCP servers, FastAPI, Django
- **Development Tools**: IDEs, linters, formatters, CI/CD configurations
- **Package Management**: npm, yarn, pip, poetry, cargo, go modules
- **Build Systems**: Vite, Webpack, Make, batch scripts, shell scripts
### Smart Command Suggestions
```bash
# Instead of generic commands, suggests project-specific ones:
User types: "node server.js"
AI suggests: "Use 'npm run dev' instead for this project"
User types: "python main.py"
AI suggests: "Use 'uvicorn main:app --reload' for this FastAPI project"
```
### Windows Optimization
- Automatically detects Windows environment
- Uses `cmd.exe` and Windows-appropriate path separators
- Suggests Windows-compatible commands (e.g., `dir` instead of `ls`)
- Handles Windows-specific Python and Node.js patterns
### Memory Integration
All learned conventions are stored as high-importance memories that:
- Appear in AI context for every interaction
- Persist across sessions and project switches
- Include environment warnings and project-specific guidance
- Prevent repeated incorrect command suggestions
## ๐ง Configuration Options
Configure via environment variables:
| Variable | Default | Description |
|----------|---------|-------------|
| `LOG_LEVEL` | `INFO` | Logging level (DEBUG, INFO, WARNING, ERROR) |
| `MAX_MEMORY_ITEMS` | `1000` | Maximum memories per project |
| `MAX_CONTEXT_TOKENS` | `8000` | Token threshold for auto-compression |
| `CLEANUP_INTERVAL_HOURS` | `24` | Auto-cleanup interval |
| `ENABLE_AUTO_CLEANUP` | `true` | Enable automatic cleanup |
| `MAX_CONCURRENT_REQUESTS` | `5` | Max concurrent requests |
| `REQUEST_TIMEOUT` | `30` | Request timeout in seconds |
| `DATA_DIR` | ~/ClaudeMemory | Where to store data and logs |
## ๐งช Testing
This package is production-ready and does not include a test suite in the distributed version. For development or CI, refer to the repository for test scripts and additional resources.
## ๐ Performance & Monitoring
The server includes built-in performance tracking:
- **Response time monitoring** for all tools
- **Success rate tracking** with error counts
- **Memory usage statistics**
- **Database performance metrics**
- **Automatic health checks**
Access via the `get_performance_stats()` and `health_check()` tools.
## ๐๏ธ Database
- **SQLite** for reliable, file-based storage
- **Automatic schema migrations** for updates
- **Comprehensive indexing** for fast queries
- **Built-in backup and optimization** tools
- **Cross-platform compatibility**
Default location: `./data/mcp_memory.db`
## ๐ Semantic Search
Powered by sentence-transformers for intelligent memory retrieval:
- **Natural language queries** - "Find memories about database optimization"
- **Similarity-based matching** using embeddings
- **Configurable similarity thresholds**
- **Automatic model downloading** (~90MB on first run)
## ๐ง Sequential Thinking
Structured reasoning system:
- **5-stage thinking process**: Analysis โ Planning โ Execution โ Validation โ Reflection
- **Token optimization**: Real-time estimation and compression (30-70% reduction)
- **Context continuity**: Intelligent session handoffs with preserved context
- **Auto-extraction**: Automatically identifies key points, decisions, and action items
- **Performance tracking**: Monitor reasoning chains and optimization metrics
## ๐ผ Token Management
Advanced context optimization for high-scale deployments:
- **Smart compression**: Pattern-based extraction preserves essential information
- **Token estimation**: Real-time calculation for planning and budgeting
- **Context summarization**: Automatic conversion of conversations to actionable summaries
- **Session consolidation**: Seamless handoffs between conversation sessions
- **Performance analytics**: Detailed metrics on compression ratios and response times
## ๐ Logging
Comprehensive logging system:
- **Daily log rotation** in `./logs/` directory
- **Structured logging** with timestamps and levels
- **Performance tracking** integrated
- **Error tracking** with stack traces
## ๐ค Contributing
1. Fork the repository
2. Create a feature branch
3. Add tests for new functionality
4. Ensure all tests pass
5. Submit a pull request
## ๐ License
MIT License - see LICENSE file for details.
## ๐ Support
- **Issues**: [GitHub Issues](https://github.com/cbunting99/enhanced-mcp-memory/issues)
- **Documentation**: [README](https://github.com/cbunting99/enhanced-mcp-memory#readme)
- **Discussions**: [GitHub Discussions](https://github.com/cbunting99/enhanced-mcp-memory/discussions)
## ๐ท๏ธ Version History
- **v2.0.2** - Updated package build configuration and license compatibility fixes
- **v2.0.1** - Enhanced features with sequential thinking and project conventions
- **v1.2.0** - Enhanced MCP server with performance monitoring and health checks
- **v1.1.0** - Added semantic search and knowledge graph features
- **v1.0.0** - Initial release with basic memory and task management
Raw data
{
"_id": null,
"home_page": "https://github.com/cbunting99/enhanced-mcp-memory",
"name": "enhanced-mcp-memory",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "cbunting99 <cbunting99@users.noreply.github.com>",
"keywords": "mcp, memory, ai, task-management, knowledge-graph, semantic-search, sequential-thinking, project-conventions, token-optimization",
"author": "cbunting99",
"author_email": "cbunting99 <cbunting99@users.noreply.github.com>",
"download_url": "https://files.pythonhosted.org/packages/ba/da/da09417fae98d30d50f39eaf8dbd2271bbf2441bac3be60c61edf93293eb/enhanced_mcp_memory-2.0.8.tar.gz",
"platform": null,
"description": "# Enhanced MCP Memory\r\n\r\n> **\u26a1 Optimized for Claude Sonnet 4** - This MCP server works best with Claude Sonnet 4 for optimal performance and AI-powered features.\r\n\r\nAn enhanced MCP (Model Context Protocol) server for intelligent memory and task management, designed for AI assistants and development workflows. Features semantic search, automatic task extraction, knowledge graphs, and comprehensive project management.\r\n\r\n## \u2728 Key Features\r\n\r\n### \ud83e\udde0 Intelligent Memory Management\r\n- **Semantic search** using sentence-transformers for natural language queries\r\n- **Automatic memory classification** with importance scoring\r\n- **Duplicate detection** and content deduplication\r\n- **File path associations** for code-memory relationships\r\n- **Knowledge graph relationships** with automatic similarity detection\r\n\r\n### \ud83e\uddec Sequential Thinking Engine\r\n- **Structured reasoning chains** with 5-stage process (analysis, planning, execution, validation, reflection)\r\n- **Context management** with automatic token optimization\r\n- **Conversation continuity** across sessions with intelligent summarization\r\n- **Real-time token estimation** and compression (30-70% reduction)\r\n- **Auto-extraction** of key points, decisions, and action items\r\n\r\n### \ud83d\udccb Advanced Task Management\r\n- **Auto-task extraction** from conversations and code comments\r\n- **Priority and category management** with validation\r\n- **Status tracking** (pending, in_progress, completed, cancelled)\r\n- **Task-memory relationships** in knowledge graph\r\n- **Project-based organization**\r\n- **Complex task decomposition** into manageable subtasks\r\n\r\n### \ud83c\udfd7\ufe0f Project Convention Learning\r\n- **Automatic environment detection** - OS, shell, tools, and runtime versions\r\n- **Project type recognition** - Node.js, Python, Rust, Go, Java, MCP servers, etc.\r\n- **Command pattern learning** - Extracts npm scripts, Makefile targets, and project commands\r\n- **Tool configuration detection** - IDEs, linters, CI/CD, build tools, and testing frameworks\r\n- **Dependency management** - Package managers, lock files, and installation commands\r\n- **Smart command suggestions** - Corrects user commands based on project conventions\r\n- **Windows-specific optimizations** - Proper path separators and command formats\r\n- **Memory integration** - Stores learned conventions for AI context and future reference\r\n\r\n### \ud83d\udcca Performance Monitoring\r\n- **Performance monitoring** with detailed metrics\r\n- **Health checks** and system diagnostics\r\n- **Automatic cleanup** of old data and duplicates\r\n- **Database optimization** tools\r\n- **Comprehensive logging** and error tracking\r\n- **Token usage analytics** and optimization recommendations\r\n\r\n### \ufffd Enterprise Features\r\n- **Performance monitoring** with detailed metrics\r\n- **Health checks** and system diagnostics\r\n- **Automatic cleanup** of old data and duplicates\r\n- **Database optimization** tools\r\n- **Comprehensive logging** and error tracking\r\n- **Token usage analytics** and optimization recommendations\r\n\r\n### \ufffd\ud83d\ude80 Easy Deployment\r\n- **uvx compatible** for one-command installation\r\n- **Zero-configuration** startup with sensible defaults\r\n- **Environment variable** configuration\r\n- **Cross-platform** support (Windows, macOS, Linux)\r\n\r\n## \ud83c\udfd7\ufe0f Project Structure\r\n\r\n```\r\nenhanced-mcp-memory/\r\n\u251c\u2500\u2500 mcp_server_enhanced.py # Main MCP server with FastMCP integration\r\n\u251c\u2500\u2500 memory_manager.py # Core memory/task logic and project detection\r\n\u251c\u2500\u2500 sequential_thinking.py # Thinking chains and context optimization\r\n\u251c\u2500\u2500 database.py # Database operations with retry mechanisms\r\n\u251c\u2500\u2500 requirements.txt # Python dependencies\r\n\u251c\u2500\u2500 setup.py # Package configuration\r\n\u251c\u2500\u2500 data/ # SQLite database storage\r\n\u251c\u2500\u2500 logs/ # Application logs\r\n```\r\n\r\n## \ud83d\ude80 Quick Start\r\n\r\n### Option 1: Using uvx (Recommended)\r\n\r\n```bash\r\n# Install and run with uvx\r\nuvx enhanced-mcp-memory\r\n```\r\n\r\n### Option 2: Manual Installation\r\n\r\n```bash\r\n# Clone and install\r\ngit clone https://github.com/cbunting99/enhanced-mcp-memory.git\r\ncd enhanced-mcp-memory\r\npip install -e .\r\n\r\n# Run the server\r\nenhanced-mcp-memory\r\n```\r\n\r\n### Option 3: Development Setup\r\n\r\n```bash\r\n# Clone repository\r\ngit clone https://github.com/cbunting99/enhanced-mcp-memory.git\r\ncd enhanced-mcp-memory\r\n\r\n# Install dependencies\r\npip install -r requirements.txt\r\n\r\n# Run directly\r\npython mcp_server_enhanced.py\r\n```\r\n\r\n## \u2699\ufe0f MCP Configuration\r\n\r\nAdd to your MCP client configuration:\r\n\r\n### For uvx installation:\r\n```json\r\n{\r\n \"mcpServers\": {\r\n \"memory-manager\": {\r\n \"command\": \"uvx\",\r\n \"args\": [\"enhanced-mcp-memory\"],\r\n \"env\": {\r\n \"LOG_LEVEL\": \"INFO\",\r\n \"MAX_MEMORY_ITEMS\": \"1000\",\r\n \"ENABLE_AUTO_CLEANUP\": \"true\"\r\n }\r\n }\r\n }\r\n}\r\n```\r\n\r\n### For local installation:\r\n```json\r\n{\r\n \"mcpServers\": {\r\n \"memory-manager\": {\r\n \"command\": \"python\",\r\n \"args\": [\"mcp_server_enhanced.py\"],\r\n \"cwd\": \"/path/to/enhanced-mcp-memory\",\r\n \"env\": {\r\n \"LOG_LEVEL\": \"INFO\",\r\n \"MAX_MEMORY_ITEMS\": \"1000\",\r\n \"ENABLE_AUTO_CLEANUP\": \"true\"\r\n }\r\n }\r\n }\r\n}\r\n```\r\n\r\n## \ud83d\udee0\ufe0f Available Tools\r\n\r\n### Core Memory Tools\r\n- `get_memory_context(query)` - Get relevant memories and context\r\n- `create_task(title, description, priority, category)` - Create new tasks\r\n- `get_tasks(status, limit)` - Retrieve tasks with filtering\r\n- `get_project_summary()` - Get comprehensive project overview\r\n\r\n### Sequential Thinking Tools\r\n- `start_thinking_chain(objective)` - Begin structured reasoning process\r\n- `add_thinking_step(chain_id, stage, title, content, reasoning)` - Add reasoning steps\r\n- `get_thinking_chain(chain_id)` - Retrieve complete thinking chain\r\n- `list_thinking_chains(limit)` - List recent thinking chains\r\n\r\n### Context Management Tools \r\n- `create_context_summary(content, key_points, decisions, actions)` - Compress context for token optimization\r\n- `start_new_chat_session(title, objective, continue_from)` - Begin new conversation with optional continuation\r\n- `consolidate_current_session()` - Compress current session for handoff\r\n- `get_optimized_context(max_tokens)` - Get token-optimized context\r\n- `estimate_token_usage(text)` - Estimate token count for planning\r\n\r\n### Enterprise Auto-Processing\r\n- `auto_process_conversation(content, interaction_type)` - Extract memories and tasks automatically\r\n- `decompose_task(prompt)` - Break complex tasks into subtasks\r\n\r\n### Project Convention Tools\r\n- `auto_learn_project_conventions(project_path)` - Automatically detect and learn project patterns\r\n- `get_project_conventions_summary()` - Get formatted summary of learned conventions\r\n- `suggest_correct_command(user_command)` - Suggest project-appropriate command corrections\r\n- `remember_project_pattern(pattern_type, pattern, description)` - Manually store project patterns\r\n- `update_memory_context()` - Refresh memory context with latest project conventions\r\n\r\n### System Management Tools\r\n- `health_check()` - Check server health and connectivity\r\n- `get_performance_stats()` - Get detailed performance metrics\r\n- `cleanup_old_data(days_old)` - Clean up old memories and tasks\r\n- `optimize_memories()` - Remove duplicates and optimize storage\r\n- `get_database_stats()` - Get comprehensive database statistics\r\n\r\n## \ud83c\udfd7\ufe0f Project Convention Learning\r\n\r\nThe Enhanced MCP Memory Server automatically learns and remembers project-specific conventions to prevent AI assistants from suggesting incorrect commands or approaches:\r\n\r\n### Automatic Detection\r\n- **Operating System**: Windows vs Unix, preferred shell and commands\r\n- **Project Type**: Node.js, Python, Rust, Go, Java, MCP servers, FastAPI, Django\r\n- **Development Tools**: IDEs, linters, formatters, CI/CD configurations\r\n- **Package Management**: npm, yarn, pip, poetry, cargo, go modules\r\n- **Build Systems**: Vite, Webpack, Make, batch scripts, shell scripts\r\n\r\n### Smart Command Suggestions\r\n```bash\r\n# Instead of generic commands, suggests project-specific ones:\r\nUser types: \"node server.js\"\r\nAI suggests: \"Use 'npm run dev' instead for this project\"\r\n\r\nUser types: \"python main.py\" \r\nAI suggests: \"Use 'uvicorn main:app --reload' for this FastAPI project\"\r\n```\r\n\r\n### Windows Optimization\r\n- Automatically detects Windows environment\r\n- Uses `cmd.exe` and Windows-appropriate path separators\r\n- Suggests Windows-compatible commands (e.g., `dir` instead of `ls`)\r\n- Handles Windows-specific Python and Node.js patterns\r\n\r\n### Memory Integration\r\nAll learned conventions are stored as high-importance memories that:\r\n- Appear in AI context for every interaction\r\n- Persist across sessions and project switches\r\n- Include environment warnings and project-specific guidance\r\n- Prevent repeated incorrect command suggestions\r\n\r\n## \ud83d\udd27 Configuration Options\r\n\r\nConfigure via environment variables:\r\n\r\n| Variable | Default | Description |\r\n|----------|---------|-------------|\r\n| `LOG_LEVEL` | `INFO` | Logging level (DEBUG, INFO, WARNING, ERROR) |\r\n| `MAX_MEMORY_ITEMS` | `1000` | Maximum memories per project |\r\n| `MAX_CONTEXT_TOKENS` | `8000` | Token threshold for auto-compression |\r\n| `CLEANUP_INTERVAL_HOURS` | `24` | Auto-cleanup interval |\r\n| `ENABLE_AUTO_CLEANUP` | `true` | Enable automatic cleanup |\r\n| `MAX_CONCURRENT_REQUESTS` | `5` | Max concurrent requests |\r\n| `REQUEST_TIMEOUT` | `30` | Request timeout in seconds |\r\n| `DATA_DIR` | ~/ClaudeMemory | Where to store data and logs |\r\n\r\n## \ud83e\uddea Testing\r\n\r\nThis package is production-ready and does not include a test suite in the distributed version. For development or CI, refer to the repository for test scripts and additional resources.\r\n\r\n## \ud83d\udcca Performance & Monitoring\r\n\r\nThe server includes built-in performance tracking:\r\n\r\n- **Response time monitoring** for all tools\r\n- **Success rate tracking** with error counts\r\n- **Memory usage statistics**\r\n- **Database performance metrics**\r\n- **Automatic health checks**\r\n\r\nAccess via the `get_performance_stats()` and `health_check()` tools.\r\n\r\n## \ud83d\uddc4\ufe0f Database\r\n\r\n- **SQLite** for reliable, file-based storage\r\n- **Automatic schema migrations** for updates\r\n- **Comprehensive indexing** for fast queries\r\n- **Built-in backup and optimization** tools\r\n- **Cross-platform compatibility**\r\n\r\nDefault location: `./data/mcp_memory.db`\r\n\r\n## \ud83d\udd0d Semantic Search\r\n\r\nPowered by sentence-transformers for intelligent memory retrieval:\r\n\r\n- **Natural language queries** - \"Find memories about database optimization\"\r\n- **Similarity-based matching** using embeddings\r\n- **Configurable similarity thresholds**\r\n- **Automatic model downloading** (~90MB on first run)\r\n\r\n## \ud83e\udde0 Sequential Thinking\r\n\r\nStructured reasoning system:\r\n\r\n- **5-stage thinking process**: Analysis \u2192 Planning \u2192 Execution \u2192 Validation \u2192 Reflection\r\n- **Token optimization**: Real-time estimation and compression (30-70% reduction)\r\n- **Context continuity**: Intelligent session handoffs with preserved context\r\n- **Auto-extraction**: Automatically identifies key points, decisions, and action items\r\n- **Performance tracking**: Monitor reasoning chains and optimization metrics\r\n\r\n## \ud83d\udcbc Token Management\r\n\r\nAdvanced context optimization for high-scale deployments:\r\n\r\n- **Smart compression**: Pattern-based extraction preserves essential information\r\n- **Token estimation**: Real-time calculation for planning and budgeting\r\n- **Context summarization**: Automatic conversion of conversations to actionable summaries\r\n- **Session consolidation**: Seamless handoffs between conversation sessions\r\n- **Performance analytics**: Detailed metrics on compression ratios and response times\r\n\r\n## \ud83d\udcdd Logging\r\n\r\nComprehensive logging system:\r\n\r\n- **Daily log rotation** in `./logs/` directory\r\n- **Structured logging** with timestamps and levels\r\n- **Performance tracking** integrated\r\n- **Error tracking** with stack traces\r\n\r\n## \ud83e\udd1d Contributing\r\n\r\n1. Fork the repository\r\n2. Create a feature branch\r\n3. Add tests for new functionality\r\n4. Ensure all tests pass\r\n5. Submit a pull request\r\n\r\n## \ud83d\udcc4 License\r\n\r\nMIT License - see LICENSE file for details.\r\n\r\n## \ud83c\udd98 Support\r\n\r\n- **Issues**: [GitHub Issues](https://github.com/cbunting99/enhanced-mcp-memory/issues)\r\n- **Documentation**: [README](https://github.com/cbunting99/enhanced-mcp-memory#readme)\r\n- **Discussions**: [GitHub Discussions](https://github.com/cbunting99/enhanced-mcp-memory/discussions)\r\n\r\n## \ud83c\udff7\ufe0f Version History\r\n\r\n- **v2.0.2** - Updated package build configuration and license compatibility fixes\r\n- **v2.0.1** - Enhanced features with sequential thinking and project conventions\r\n- **v1.2.0** - Enhanced MCP server with performance monitoring and health checks\r\n- **v1.1.0** - Added semantic search and knowledge graph features\r\n- **v1.0.0** - Initial release with basic memory and task management\r\n",
"bugtrack_url": null,
"license": null,
"summary": "Enterprise-grade MCP server with sequential thinking, project convention learning, and intelligent memory management",
"version": "2.0.8",
"project_urls": {
"Documentation": "https://github.com/cbunting99/enhanced-mcp-memory#readme",
"Homepage": "https://github.com/cbunting99/enhanced-mcp-memory",
"Issues": "https://github.com/cbunting99/enhanced-mcp-memory/issues",
"Repository": "https://github.com/cbunting99/enhanced-mcp-memory"
},
"split_keywords": [
"mcp",
" memory",
" ai",
" task-management",
" knowledge-graph",
" semantic-search",
" sequential-thinking",
" project-conventions",
" token-optimization"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "81ae84cba30aaa6711ae85d831158620f6140631653ef7e35ead324e8c2eb956",
"md5": "8720aa377140a125dc3feea4e3923d2f",
"sha256": "e3175ee5d201963d33219ec82b8870386c7a6cfe4eace9772252ac0cf63cea6a"
},
"downloads": -1,
"filename": "enhanced_mcp_memory-2.0.8-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8720aa377140a125dc3feea4e3923d2f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 41902,
"upload_time": "2025-08-04T15:35:20",
"upload_time_iso_8601": "2025-08-04T15:35:20.996080Z",
"url": "https://files.pythonhosted.org/packages/81/ae/84cba30aaa6711ae85d831158620f6140631653ef7e35ead324e8c2eb956/enhanced_mcp_memory-2.0.8-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "badada09417fae98d30d50f39eaf8dbd2271bbf2441bac3be60c61edf93293eb",
"md5": "f12dd631035752f25a282bc69dde5dae",
"sha256": "3b529299529f85b86e6c533f3e598627be40ad29ada0bbfb8b2ba9c92836cf1f"
},
"downloads": -1,
"filename": "enhanced_mcp_memory-2.0.8.tar.gz",
"has_sig": false,
"md5_digest": "f12dd631035752f25a282bc69dde5dae",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 46613,
"upload_time": "2025-08-04T15:35:22",
"upload_time_iso_8601": "2025-08-04T15:35:22.109461Z",
"url": "https://files.pythonhosted.org/packages/ba/da/da09417fae98d30d50f39eaf8dbd2271bbf2441bac3be60c61edf93293eb/enhanced_mcp_memory-2.0.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-04 15:35:22",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "cbunting99",
"github_project": "enhanced-mcp-memory",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "fastmcp",
"specs": [
[
">=",
"2.10.5"
]
]
},
{
"name": "python-dotenv",
"specs": [
[
">=",
"1.0.0"
]
]
},
{
"name": "sentence-transformers",
"specs": [
[
">=",
"2.2.0"
]
]
},
{
"name": "numpy",
"specs": [
[
">=",
"1.21.0"
]
]
},
{
"name": "scipy",
"specs": [
[
">=",
"1.7.0"
]
]
},
{
"name": "filelock",
"specs": [
[
">=",
"3.0.0"
]
]
}
],
"lcname": "enhanced-mcp-memory"
}
JSON
