Price Per TokenPrice Per Token
Memory Box MCP Server

Memory Box MCP Server

by amotivv

0

About

Memory Box is a semantic memory storage and retrieval system that enables intelligent organization and recall of information using vector embeddings. It allows users to save, search, and manage memories with contextual understanding rather than simple keyword matching. Key features: - Save memories with metadata, source information, and automatic vector embeddings - Semantic search capabilities to find memories based on meaning and context - Organize memories into customizable buckets for structured categorization - Retrieve related memories through semantic similarity matching - Update, delete, and monitor memory processing status - Format memories according to structured system prompts - Track usage statistics and resource limits Requires a Memory Box instance (self-hosted or using the hosted service at memorybox.amotivv.ai) with API token configuration.

README

Memory Box MCP Server

Cline and Claude Desktop MCP integration for Memory Box - save, search, and format memories with semantic understanding

This MCP server provides tools for interacting with a Memory Box instance, allowing you to save and search memories using semantic search directly from Cline and Claude Desktop.

Related Projects

This MCP server is designed to work with Memory Box, a semantic memory storage and retrieval system powered by vector embeddings.

Memory Box provides the backend API that this MCP server communicates with, allowing you to:

  • Store memories with vector embeddings for semantic search
  • Organize memories into customizable buckets
  • Search for memories based on meaning, not just keywords
  • Retrieve memories with detailed context
  • Find semantically related memories
  • Track memory processing status
  • For more information about Memory Box, including how to set up your own instance, please visit the Memory Box website.

    Features

  • Save Memories: Save formatted memories to your Memory Box with source information and metadata
  • Search Memories: Search your memories using semantic search with pagination and date sorting
  • Retrieve Memories: Get all memories or memories from specific buckets
  • Bucket Management: Create and delete buckets for organizing memories
  • Memory Management: Update or delete existing memories
  • Find Related Memories: Discover semantically similar memories
  • Check Memory Status: Monitor the processing status of your memories
  • Format Memories: Format memories according to a structured system prompt
  • Usage Statistics: View your current plan, usage metrics, and resource limits
  • Installation

    The server has been installed and configured for use with Cline. Note that you need a running Memory Box instance (either self-hosted or using the hosted version at memorybox.amotivv.ai) to use this MCP server.

    Installing as Claude Desktop Extension (Recommended)

    The easiest way to use Memory Box with Claude Desktop is through the Desktop Extension:

    1. Download the latest memory-box.mcpb file from the releases page 2. Open Claude Desktop 3. Go to Settings > Extensions 4. Click "Install from file" 5. Select the downloaded memory-box.mcpb file 6. Configure your Memory Box API token in the extension settings

    The extension will automatically configure all necessary environment variables and tools.

    Installing via Smithery

    To install Memory Box MCP Server for Claude Desktop automatically via Smithery:

    npx -y @smithery/cli install @amotivv/memory-box-mcp --client claude
    

    To complete the setup:

    1. Edit the Cline MCP settings file at:

       ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
       

    2. Add your Memory Box token to the MEMORY_BOX_TOKEN environment variable:

       "memory-box-mcp": {
         "command": "node",
         "args": [
           "/build/index.js"
         ],
         "env": {
           "MEMORY_BOX_API_URL": "https://memorybox.amotivv.ai",
           "MEMORY_BOX_TOKEN": "your-token-here",
           "DEFAULT_BUCKET": "General"
         },
         "disabled": false,
         "autoApprove": []
       }
       

    3. Optionally, you can customize the default bucket by changing the DEFAULT_BUCKET value.

    Usage

    Once configured, you can use the following tools in Cline:

    Save Memory

    Save a memory to Memory Box with proper formatting:

    Use the save_memory tool to save this information about vector databases: "Vector databases like pgvector store and query high-dimensional vectors for semantic search applications."
    

    Parameters:

  • text (required): The memory content to save
  • bucket_id (optional): The bucket to save the memory to (default: "General")
  • format (optional): Whether to format the memory according to the system prompt (default: true)
  • type (optional): The type of memory (TECHNICAL, DECISION, SOLUTION, CONCEPT, REFERENCE, APPLICATION, FACT) for formatting (default: "TECHNICAL")
  • source_type (optional): Type of memory source (default: "llm_plugin")
  • reference_data (optional): Additional metadata about the memory source and context
  • Search Memories

    Search for memories using semantic search:

    ``` Use the search_memories tool to find information about "vector data

    Related MCP Servers

    AI Research Assistant

    AI Research Assistant

    hamid-vakilzadeh

    AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar

    Web & Search
    12 8
    Linkup

    Linkup

    LinkupPlatform

    Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages

    Web & Search
    2 24
    Math-MCP

    Math-MCP

    EthanHenrickson

    Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support

    Developer Tools
    22 81