{"type":"mcp_server","name":"mcp-memory-service","description":"This repository provides an MCP server for Claude Desktop, enabling semantic memory and persistent storage using ChromaDB and sentence transformers. It offers features like natural language recall, tag-based retrieval, and cross-platform compatibility.","category":"AI","language":"Python","stars":1911,"forks":17,"owner":"doobidoo","github_url":"https://github.com/doobidoo/mcp-memory-service","homepage":null,"setup":"## Setup\n\n**Quick Start (Recommended)**\n\n1.  Clone the repository: `git clone https://github.com/doobidoo/mcp-memory-service.git`\n2.  Change directory: `cd mcp-memory-service`\n3.  Create a virtual environment: `python -m venv venv`\n4.  Activate the virtual environment: `source venv/bin/activate` (On Windows: `venv\\Scripts\\activate`)\n5.  Run the installation script: `python install.py`\n\n**Windows Installation (Special Case)**\n\n1.  After activating your virtual environment, run: `python scripts/install_windows.py`\n\n**Installing via Smithery**\n\n1.  Run: `npx -y @smithery/cli install @doobidoo/mcp-memory-service --client claude`\n\n**Claude MCP Configuration**\n\n*   Standard Configuration: Add the provided JSON configuration to your `claude_desktop_config.json` file, adjusting the directory and path variables.\n*   Windows-Specific Configuration (Recommended): Add the provided JSON configuration to your `claude_desktop_config.json` file, adjusting the path variables.\n\n**Usage**\n\n*   To run the memory server directly (for testing): `python scripts/run_memory_server.py`\n*   For isolated testing of methods: `python src/chroma_test_isolated.py`","tools":"## Available Tools\n\n1.  Semantic search (using sentence transformers).\n2.  Natural language time-based recall (e.g., \"last week\", \"yesterday morning\").\n3.  Tag-based memory retrieval system.\n4.  Persistent storage (using ChromaDB).\n5.  Automatic database backups.\n6.  Memory optimization tools.\n7.  Exact match retrieval.\n8.  Debug mode (for similarity analysis).\n9.  Database health monitoring.\n10. Duplicate detection and cleanup.\n11. Customizable embedding model.\n12. Cross-platform compatibility (Apple Silicon, Intel, Windows, Linux).\n13. Hardware-aware optimizations (for different environments).\n14. Graceful fallbacks (for limited hardware resources).\n15. Core Memory Operations (store, retrieve, recall, search, exact match, debug).\n16. Database Management (backup, stats, optimize, health, model check).\n17. Memory Management (delete, delete by tag, cleanup duplicates).","faq":null,"created_at":"2024-12-26T10:15:44+00:00","updated_at":"2025-03-28T16:02:46+00:00","source_url":"https://model-context-protocol.com/servers/mcp-claude-semantic-memory-chromadb-server","related_articles":[]}