Skip to content

spokV/memory-mcp

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MCP Memory Server

A lightweight Model Context Protocol (MCP) server that persists shared memories in SQLite. Compatible with Claude Code, Codex CLI, and other MCP-aware clients.

Features

  • Persistent Storage - SQLite-backed database with optional cloud sync (S3, GCS, Azure)
  • Semantic Search - Vector embeddings (TF-IDF, sentence-transformers, or OpenAI)
  • Event Notifications - Poll-based system for inter-agent communication
  • Advanced Queries - Full-text search, date ranges, tag filters (AND/OR/NOT)
  • Cross-references - Auto-linked related memories based on similarity
  • Hierarchical Organization - Explore memories by section/subsection
  • Export/Import - Backup and restore with merge strategies
  • Statistics & Analytics - Tag usage, trends, and connection insights
  • Zero Dependencies - Works out-of-box with Python stdlib (optional backends available)

Install

# From GitHub
pip install git+https://github.com/spokV/memory-mcp.git

# For cloud storage (S3/R2/GCS/Azure), install boto3 separately
pip install boto3

# Or from local clone with extras
pip install -e ".mcp/src/memory-mcp[cloud]"  # includes boto3
pip install -e ".mcp/src/memory-mcp[all]"    # includes cloud + dev tools

Usage

The server runs automatically when configured in Claude Code. Manual invocation:

# Default (stdio mode)
memory-mcp-server

# HTTP endpoint
memory-mcp-server --transport streamable-http --host 127.0.0.1 --port 8765

Claude Code Config

Add to .mcp.json in your project root:

Local DB

{
  "mcpServers": {
    "memory": {
      "command": "{$HOME}/miniconda/bin/memory-mcp-server",
      "args": [],
      "env": {
        "MEMORY_MCP_DB_PATH": "{$HOME}/.local/share/memory-mcp/memories.db",
        "MEMORY_MCP_ALLOW_ANY_TAG": "1"
      }
    }
  }
}

Cloud DB (S3/R2)

{
  "mcpServers": {
    "memory": {
      "command": "/opt/conda/bin/memory-mcp-server",
      "args": [],
      "env": {
        "AWS_ENDPOINT_URL": "https://xxxxxxx.r2.cloudflarestorage.com",
        "MEMORY_MCP_STORAGE_URI": "s3://memories/memories.db",
        "MEMORY_MCP_CLOUD_ENCRYPT": "true",
        "MEMORY_MCP_ALLOW_ANY_TAG": "1"
      }
    }
  }
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Packages

No packages published

Contributors 2

  •  
  •  

Languages