MCP ExplorerExplorer

Memory Pickle Mcp

@Justar96on 4 days ago
8 Apache-2.0
FreeCommunity
AI Systems
A Model Context Protocol server that gives AI agents precise memory for project management.

Overview

What is Memory Pickle Mcp

Memory Pickle MCP is a project management and session memory tool designed for AI agents. It offers essential tools to track projects, tasks, and context during conversational sessions, facilitating effective management and continuity in interactions.

Use cases

The MCP is ideal for collaborative projects where multiple tasks need to be tracked and updated in real-time. It is particularly suited for AI agents that require memory retention only during active sessions, such as during coding or troubleshooting tasks.

How to use

Users can start using MCP by installing the package via NPX or globally. Once set up, they can utilize tools like create_project and create_task to manage tasks and projects. It also includes a memory system for storing context and generating handoff summaries for session transitions.

Key features

Key features of Memory Pickle MCP include hierarchical task management, project organization, categorized memory storage, and the ability to generate handoff summaries. It supports session continuity by maintaining context and progress across tasks.

Where to use

Memory Pickle MCP can be used in environments that involve AI interactions requiring project management, such as software development, research teams, and customer support where session continuity and real-time task tracking are essential.

Content

Memory Pickle MCP

Project management and session memory for AI agents. Provides 13 comprehensive MCP tools for tracking projects, tasks, and context during AI coding sessions.

suggestion

for kilo , cline , roo perform best with code mode your agent will not lose track. there are some struggle with HITL

Quick Start

Pre-release Version (Latest Development)

{
  "mcpServers": {
    "memory-pickle-pre": {
      "command": "npx",
      "args": [
        "-y",
        "@cabbages-pre/memory-pickle-mcp-pre@latest"
      ]
    }
  }
}

Stable Version

{
  "mcpServers": {
    "memory-pickle": {
      "command": "npx",
      "args": [
        "-y",
        "@cabbages/memory-pickle-mcp@latest"
      ]
    }
  }
}

Local Development

{
  "mcpServers": {
    "memory-pickle-dev": {
      "command": "node",
      "args": [
        "build/index.js"
      ],
      "cwd": "/path/to/your/memory-pickle-mcp"
    }
  }
}

AI Assistant Compatibility

Extensively Tested & Optimized For:

  • Cursor , Windsurf , Cline, Roo, Kilo Mode Code

Additional Support:

  • Claude Desktop (direct MCP integration)
  • VS Code with MCP extensions

Architecture Overview

Memory-Only Storage Architecture:

  • All data exists only during the current chat session
  • No files created on disk - zero filesystem dependencies
  • Data automatically cleared when session ends
  • Blazing fast performance with in-memory operations
  • Complete session isolation for security

13-Tool Comprehensive System:

  • 4 Read Tools: State recall, task listing, project overview, detailed task info
  • 5 Write Tools: Project/task creation and updates, context switching
  • 2 Memory Tools: Information storage and contextual search
  • 2 Session Tools: Data export and handoff summary generation

Features

Hierarchical Task Organization

# Create parent task
create_task:
  title: "Build Authentication System"
  priority: "high"

# Create subtasks
create_task:
  title: "Implement login API"
  parent_id: "task_123"  # Links to parent
  
create_task:
  title: "Add password reset flow"
  parent_id: "task_123"

Progress Tracking & Blockers

# Comprehensive task updates
update_task:
  task_id: "task_123"
  progress: 75
  notes: ["API endpoints complete", "Working on validation"]
  blockers: ["Waiting for security review", "Database schema pending"]
  completed: false

Memory System with Importance

# Store critical decisions
remember_this:
  content: "Switched from JWT to session cookies for security"
  importance: "critical"
  project_id: "proj_auth"

# Search by importance level
recall_context:
  query: "security decision"
  importance: "critical"
  limit: 5

Session Workflow

Session Handoff

# Generate clean transition summary
generate_handoff_summary:
  format: "detailed"
  project_id: "current"

# Export for permanent storage
export_session:
  format: "markdown"
  include_handoff: true
  raw_markdown: true  # Clean output for processing

⚠️ Agent Integration Notes

  • Context switching: Agents may lose context between tool calls (in some case)
  • State synchronization: Use recall_state to refresh context
  • Error handling: Tools provide detailed error information
    send me issues <3

Requirements

  • Node.js: 16.0.0 or higher
  • MCP Client: Claude Desktop, Cursor, Windsurf, Cline, Roo, etc.
  • Memory: 100MB RAM minimum for typical usage
  • Platform: Windows, macOS, Linux (cross-platform)

Links & Resources

Documentation

Troubleshooting

Tools Not Working

  1. Update to latest version: npx -y @cabbages/memory-pickle-mcp Use @latest flag
  2. Verify MCP client configuration in settings
  3. Check Node.js version: node --version
  4. Restart MCP server for complete reset

Data Loss Prevention

  1. Tell Agent to use generate_handoff_summary before ending sessions
  2. Export critical data with export_session
  3. Save important decisions as markdown files
  4. Document project state in external files

Version Information

Current Version: 1.3.9

Recent Changes:

  • 13 comprehensive tools for complete project management
  • Advanced hierarchical task organization with parent-child relationships
  • Code location linking for development context
  • Importance-based memory classification system
  • Comprehensive session export and handoff capabilities
  • Optimized for modern AI coding assistants (Cursor, Cline, Roo, etc.)

License

Apache 2.0 - See LICENSE for details

Tools

No tools

Comments