MCPgee
MCPgee
MCPgeeMCPgee

Memory Journal

v1.0.0•Knowledge & Memory•stable

Secure AI Memory with Dynamic Project Detection, Automatic Session Briefing, Personal+Team Session Summary Prompts, Triple Search, Knowledge Graphs, GitHub Integration (Issues, PRs, Actions, Kanban, Milestones), Team Collaboration, Hush, Adaptive Ana

ai-agentai-contextcode-modecontext-engineeringcontext-management
Share:
16
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Memory Journal?

Memory Journal is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to secure ai memory with dynamic project detection, automatic session briefing, personal+team session summary prompts, triple search, knowledge graphs, github integration (issues, prs, actions, kanban, m...

Secure AI Memory with Dynamic Project Detection, Automatic Session Briefing, Personal+Team Session Summary Prompts, Triple Search, Knowledge Graphs, GitHub Integration (Issues, PRs, Actions, Kanban, Milestones), Team Collaboration, Hush, Adaptive Ana

This server falls under the Knowledge & Memory and Developer Tools categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Secure AI Memory with Dynamic Project Detection, Automatic S

Use Cases

Project context tracking and retrieval
Team collaboration summaries
GitHub integration for issues and PRs
neverinfamous

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y memory-journal-mcp-server

Manual Installation

npx -y memory-journal-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Memory Journal

Memory Journal is a comprehensive AI memory and knowledge management MCP server that persists context across fragmented AI sessions using a SQLite database with full-text and semantic vector search. It provides 73 tools spanning personal journal entries, GitHub integration (issues, PRs, Kanban, milestones), team collaboration with a structured Hush Protocol for async flagging, and knowledge graphs with relationship visualization. Developers use it to give AI assistants persistent memory of their projects, decisions, and work history without relying on conversation context windows.

Prerequisites

  • Node.js 18 or later installed
  • A GitHub Personal Access Token with repo scope (for GitHub integration features)
  • npx available in your PATH
  • An MCP-compatible client such as Claude Desktop
  • Optional: a local git repository path for project-aware context detection
1

Install the package globally or use npx

Install memory-journal-mcp-server globally for persistent use, or use npx to run it directly without installing.

npm install -g memory-journal-mcp-server
# Or run without installing:
npx -y memory-journal-mcp-server
2

Create a GitHub Personal Access Token

Go to GitHub Settings > Developer settings > Personal access tokens and create a token with 'repo' scope. This enables the 18 GitHub tools for issues, PRs, Kanban boards, and milestones.

3

Add the server to Claude Desktop config

Edit your Claude Desktop configuration file and add the memory-journal block with your GitHub token, project registry, and allowed filesystem roots. DB_PATH sets where the SQLite database is stored.

{
  "mcpServers": {
    "memory-journal-mcp": {
      "command": "memory-journal-mcp-server",
      "env": {
        "DB_PATH": "/Users/yourname/.memory-journal.db",
        "GITHUB_TOKEN": "ghp_your_token_here",
        "PROJECT_REGISTRY": "{\"my-repo\":{\"path\":\"/path/to/repo\",\"project_number\":1}}",
        "ALLOWED_IO_ROOTS": "/path/to/repo"
      }
    }
  }
}
4

Restart Claude Desktop

Quit and reopen Claude Desktop. The server will initialize the SQLite database at DB_PATH on first start and register all 73 tools.

5

Request a session briefing

At the start of each work session, ask Claude to read your memory briefing. The server returns about 350 tokens of dynamic context including recent entries, Git status, CI health, and active team flags.

Memory Journal Examples

Client configuration

Claude Desktop config with GitHub token and project registry for a single repository.

{
  "mcpServers": {
    "memory-journal-mcp": {
      "command": "memory-journal-mcp-server",
      "env": {
        "DB_PATH": "/Users/yourname/.memory-journal.db",
        "GITHUB_TOKEN": "ghp_your_token_here",
        "PROJECT_REGISTRY": "{\"my-repo\":{\"path\":\"/path/to/my-repo\",\"project_number\":1}}",
        "ALLOWED_IO_ROOTS": "/path/to/my-repo"
      }
    }
  }
}

Prompts to try

Example prompts covering memory creation, search, GitHub integration, and team collaboration.

- "Give me my session briefing for today"
- "Save a journal entry: 'Decided to use PostgreSQL over MySQL for the auth service because of JSONB support'"
- "Search my memory for anything related to the authentication refactor"
- "List open GitHub issues in my-repo labeled 'bug'"
- "Show me the Kanban board for project 1 in my-repo"
- "Flag a blocker: the staging database is down and blocking PR #42"

Troubleshooting Memory Journal

GitHub tools return 401 or 403 errors

Check that GITHUB_TOKEN is set correctly and has 'repo' scope. For private repositories, ensure the token has access to the specific org or repo. Token values starting with 'ghp_' are classic PATs; fine-grained tokens need explicit repository permissions.

Semantic search returns no results even though entries exist

Semantic vector search requires entries to be indexed after creation. If you migrated from an older version, run the re-indexing tool or create a new entry to trigger index generation. Also check that DB_PATH points to the correct database file.

PROJECT_REGISTRY JSON causes a parse error on startup

The PROJECT_REGISTRY value must be valid JSON embedded as a string, with internal quotes escaped. Use an online JSON validator on your registry string. Alternatively, store the registry as a file and reference its path if your client supports file-based env loading.

Frequently Asked Questions about Memory Journal

What is Memory Journal?

Memory Journal is a Model Context Protocol (MCP) server that secure ai memory with dynamic project detection, automatic session briefing, personal+team session summary prompts, triple search, knowledge graphs, github integration (issues, prs, actions, kanban, milestones), team collaboration, hush, adaptive ana It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Memory Journal?

Install via npm with the command: npx -y memory-journal-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Memory Journal?

Memory Journal works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Memory Journal free to use?

Yes, Memory Journal is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Memory Journal Alternatives — Similar Knowledge & Memory Servers

Looking for alternatives to Memory Journal? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.

MemPalace

★ 52.6k

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically

Kratos

★ 25.7k

🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.

Context Mode

★ 15.4k

An MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm

Memu

★ 13.7k

Memory for 24/7 proactive agents like OpenClaw.

MemOS

★ 9.3k

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u

Everos

★ 5.4k

Build, evaluate, and integrate long-term memory for self-evolving agents.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Knowledge & MemoryDeveloper ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "memory-journal": { "command": "npx", "args": ["-y", "memory-journal-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Memory Journal?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides