Memory Journal MCP Server

Last Updated October 18, 2025 8:24 PM EST - Production/Stable v1.1.3

A production-ready developer journal with knowledge graphs, visual relationship mapping, and intelligent search

🎉 Now Production/Stable! Memory Journal has graduated from beta with powerful relationship mapping, 10x faster startup, and comprehensive documentation.

🚀 Quick Deploy:

PyPI Package - pip install memory-journal-mcp
Docker Hub - Alpine-based (225MB) with full semantic search
MCP Registry - Discoverable by MCP clients

📚 Full Documentation: GitHub Wiki

✨ What's New in v1.1.3

🎉 Production/Stable Release

Memory Journal has officially graduated from beta! This release includes:

15 MCP tools (up from 13)
8 workflow prompts (up from 6)
3 MCP resources (up from 2)
17 comprehensive wiki pages
Automatic schema migrations
Production-grade stability

🔗 Entry Relationships & Knowledge Graphs

Build connections between your entries with typed relationships:

references - General connections between work
implements - Link implementations to specs/designs
clarifies - Add explanations and elaborations
evolves_from - Track how ideas develop over time
response_to - Thread conversations and replies

📊 Visual Relationship Mapping

Generate beautiful Mermaid diagrams showing how your work connects:

graph TD
    E55["#55: Implementing visualization feature<br/>development_note"]
    E56["#56: Testing the new tool<br/>technical_note"]
    E57["#57: Documentation improvements<br/>enhancement"]
    
    E56 ==>|implements| E55
    E57 -.->|clarifies| E55
    
    style E55 fill:#FFF3E0
    style E56 fill:#FFF3E0
    style E57 fill:#FFF3E0

⚡ Performance Revolution

10x faster startup - Lazy loading reduces init time from 14s → 2-3s
Thread-safe operations - Zero race conditions in concurrent tag creation
Database lock prevention - Single-connection transactions eliminate conflicts
Optimized queries - Strategic indexes for relationship traversal

🛠️ New Tools (15 Total, +2 from v1.0)

visualize_relationships - Generate Mermaid diagrams with depth control
link_entries - Create typed relationships between entries
Plus comprehensive CRUD, triple search, analytics, and export

🎯 Enhanced Workflow Prompts (8 Total, +2 from v1.0)

find-related - Discover connected entries via semantic similarity
prepare-standup - Daily standup summaries
prepare-retro - Sprint retrospectives
weekly-digest - Day-by-day weekly summaries
analyze-period - Deep period analysis with insights
goal-tracker - Milestone and achievement tracking
get-context-bundle - Project context with Git/GitHub
get-recent-entries - Formatted recent entries

📡 New Resources (3 Total, +1 from v1.0)

memory://graph/recent - NEW Live Mermaid diagram of recent relationships
memory://recent - 10 most recent entries
memory://significant - Significant milestones and breakthroughs

🗄️ Database Improvements

Automatic schema migrations (seamless v1.0 → v1.1 upgrades)
Soft delete support with deleted_at column
New relationships table with cascading deletes
Enhanced indexes for optimal query performance

🚀 Quick Start

Option 1: PyPI (Fastest - 30 seconds)

Step 1: Install the package

pip install memory-journal-mcp

Step 2: Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "memory-journal": {
      "command": "memory-journal-mcp"
    }
  }
}

Step 3: Restart Cursor

Restart Cursor or your MCP client, then start journaling!

Option 2: Docker (Full Features - 2 minutes)

Step 1: Pull the Docker image

docker pull writenotenow/memory-journal-mcp:latest

Step 2: Create data directory

mkdir data

Step 3: Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "memory-journal": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i", 
        "-v", "./data:/app/data",
        "writenotenow/memory-journal-mcp:latest",
        "python", "src/server.py"
      ]
    }
  }
}

Step 4: Restart Cursor

Restart Cursor or your MCP client, then start journaling!

⚡ Install to Cursor IDE

One-Click Installation

Click the button below to install directly into Cursor:

Or copy this deep link:

cursor://anysphere.cursor-deeplink/mcp/install?name=Memory%20Journal%20MCP&config=eyJtZW1vcnktam91cm5hbCI6eyJhcmdzIjpbInJ1biIsIi0tcm0iLCItaSIsIi12IiwiLi9kYXRhOi9hcHAvZGF0YSIsIndyaXRlbm90ZW5vdy9tZW1vcnktam91cm5hbC1tY3A6bGF0ZXN0IiwicHl0aG9uIiwic3JjL3NlcnZlci5weSJdLCJjb21tYW5kIjoiZG9ja2VyIn19

Prerequisites

✅ Docker installed and running
✅ ~500MB disk space for data directory

Configuration

After installation, Cursor will use this Docker-based configuration. If you prefer manual setup, add this to your ~/.cursor/mcp.json:

{
  "memory-journal": {
    "command": "docker",
    "args": [
      "run", "--rm", "-i",
      "-v", "./data:/app/data",
      "writenotenow/memory-journal-mcp:latest",
      "python", "src/server.py"
    ]
  }
}

📖 See Full Installation Guide →

📋 Core Capabilities

🛠️ 15 MCP Tools - Complete Development Workflow

Entry Management:

create_entry / create_entry_minimal - Create entries with auto-context
update_entry - Edit existing entries (thread-safe)
delete_entry - Soft or permanent deletion
get_entry_by_id - Retrieve with full relationship details

Search & Discovery:

search_entries - FTS5 full-text search with highlighting
search_by_date_range - Time-based filtering with tags
semantic_search - ML-powered similarity (optional)
get_recent_entries - Quick access to recent work

Relationships & Visualization:

link_entries - Create typed relationships
visualize_relationships - Generate Mermaid diagrams

Organization & Analytics:

list_tags - Tag usage statistics
get_statistics - Comprehensive analytics by time period
export_entries - JSON/Markdown export
test_simple - Connectivity testing

🎯 8 Workflow Prompts - Automated Productivity

prepare-standup - Daily standup summaries from recent entries
prepare-retro - Sprint retrospectives with achievements and learnings
weekly-digest - Day-by-day weekly summaries
analyze-period - Deep analysis with pattern insights
goal-tracker - Milestone and achievement tracking
find-related - Discover connected entries via semantic similarity
get-context-bundle - Complete project context (Git + GitHub)
get-recent-entries - Formatted display of recent work

🔍 Triple Search System - Find Anything, Any Way

Full-text search - SQLite FTS5 with result highlighting and rank ordering
Date range search - Time-based filtering with tag and type filters
Semantic search - FAISS vector similarity for concept-based discovery (optional)

🔗 Entry Relationships - Build Your Knowledge Graph

5 relationship types - references, implements, clarifies, evolves_from, response_to
Bidirectional linking - See both incoming and outgoing relationships
Graph visualization - Generate Mermaid diagrams with depth control
Smart discovery - Find related entries via semantic similarity and shared tags

📊 Comprehensive Analytics - Track Your Progress

Entry counts by type (achievements, notes, milestones, etc.)
Top tags with usage statistics
Activity patterns by day/week/month
Significant milestone tracking
Export-ready statistics for reports

🎨 Visual Relationship Graphs - See How Work Connects

3 visualization modes - Entry-centric, tag-based, recent activity
Customizable depth - Control relationship traversal (1-3 hops)
Tag filtering - Focus on specific projects or topics
Color-coded nodes - Personal (blue) vs Project (orange) entries
Typed arrows - Different styles for different relationship types

🔄 Git & GitHub Integration - Automatic Context Capture

Repository name and path
Current branch
Latest commit (hash + message)
Recent GitHub issues (via gh CLI)
Working directory
Timestamp for all context

📦 Data Export - Own Your Data

JSON format - Machine-readable with full metadata
Markdown format - Human-readable with beautiful formatting
Flexible filtering - By date range, tags, entry types
Portable - Take your journal anywhere

📖 Usage Examples

Create an Entry with Relationships

// Create a technical achievement
create_entry({
  content: "Implemented lazy loading for ML dependencies - 10x faster startup!",
  entry_type: "technical_achievement",
  tags: ["performance", "optimization", "ml"],
  significance_type: "technical_breakthrough"
})
// Returns: Entry #55

// Link related work
link_entries({
  from_entry_id: 56,  // Testing entry
  to_entry_id: 55,    // Implementation
  relationship_type: "implements"
})

// Visualize the connections
visualize_relationships({
  entry_id: 55,
  depth: 2
})

Search and Analyze

// Full-text search with highlighting
search_entries({ query: "performance optimization", limit: 5 })

// Semantic search for concepts
semantic_search({ query: "startup time improvements", limit: 3 })

// Date range with tags
search_by_date_range({
  start_date: "2025-10-01",
  end_date: "2025-10-31",
  tags: ["performance"]
})

// Get analytics
get_statistics({ group_by: "week" })

Generate Visual Maps

// Visualize entry relationships
visualize_relationships({
  entry_id: 55,  // Root entry
  depth: 2       // 2 hops out
})

// Filter by tags
visualize_relationships({
  tags: ["visualization", "relationships"],
  limit: 20
})

// Access live graph resource
memory://graph/recent  // Most recent 20 entries with relationships

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐
│ MCP Server Layer (Async/Await)                              │
│  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────┐  │
│  │ Entry Creation  │  │ Triple Search   │  │ Relationship│  │
│  │ with Context    │  │ FTS5/Date/ML    │  │ Mapping     │  │
│  └─────────────────┘  └─────────────────┘  └─────────────┘  │
├─────────────────────────────────────────────────────────────┤
│ Thread Pool Execution Layer                                 │
│  ┌─────────────────┐  ┌─────────────────┐  ┌─────────────┐  │
│  │ Git Operations  │  │ Database Ops    │  │ Lazy ML     │  │
│  │ (2s timeout)    │  │ Single Conn     │  │ Loading     │  │
│  └─────────────────┘  └─────────────────┘  └─────────────┘  │
├─────────────────────────────────────────────────────────────┤
│ SQLite Database with FTS5 + Relationships                   │
│  ┌─────────────────────────────────────────────────────────┐│
│  │ entries + tags + relationships + embeddings + FTS       ││
│  └─────────────────────────────────────────────────────────┘│
└─────────────────────────────────────────────────────────────┘

🔧 Technical Highlights

Performance & Security

Python 3.14 - Latest Python with free-threaded support (PEP 779), deferred annotations (PEP 649), and performance optimizations
10x faster startup - Lazy loading of ML dependencies (2-3s vs 14s)
Thread-safe operations - Zero race conditions in tag creation
WAL mode - Better concurrency and crash recovery
Database lock prevention - Single-connection transactions
Aggressive timeouts - Git operations fail-fast (2s per command)
Input validation - Length limits, parameterized queries, SQL injection prevention

Semantic Search (Optional)

Model: all-MiniLM-L6-v2 (384-dimensional embeddings)
Storage: FAISS index for fast similarity search
Graceful degradation: Works perfectly without ML dependencies

Data & Privacy

Local-first: Single SQLite file, you own your data
Portable: Move your .db file anywhere
Secure: No external API calls, non-root Docker containers

📚 Documentation

Full documentation available on the GitHub Wiki:

GitHub Gists: Practical Examples & Use Cases

→ View All Memory Journal Gists

Explore 5 curated gists with real-world examples and implementation patterns:

Complete Feature Showcase - All 15 tools, 8 prompts, and 3 resources
Relationship Mapping & Knowledge Graphs - Build knowledge graphs with typed relationships
Triple Search System Guide - Master FTS5, date range, and semantic search
Workflow Automation & Prompts - Standup, retrospectives, and weekly digests
Git Integration & Context Capture - Automatic project context from Git and GitHub

🔗 Resources

GitHub Wiki - Complete documentation
GitHub Gists - 5 practical examples and use cases
Docker Hub - Container images
PyPI Package - Python package
MCP Registry - Official MCP listing
GitHub Issues - Bug reports & feature requests
Adamic Support - Project announcements

📄 License

MIT License - See LICENSE file for details.

🤝 Contributing

Built by developers, for developers. PRs welcome! See CONTRIBUTING.md for guidelines.

neverinfamous-memory-journal-mcp

Documentation