MCP Container

kratos-mcp

Kratos MCPは、AIコーディングツールのためのメモリシステムで、プロジェクトのアーキテクチャやパターンをAIが記憶し、セッション間で情報を保持します。これにより、開発者は毎回説明する手間を省き、効率的に作業を進めることができます。特に、AIツールがセッション間で情報を忘れる問題を解決するために設計されています。

GitHubWebsiteDocs

GitHubスター

9

ユーザー評価

未評価

お気に入り

0

閲覧数

4

フォーク

1

イシュー

0

README
🏛️ Kratos MCP
Memory System for AI Coding Tools

npm version
License: MIT
MCP Compatible
TypeScript

Never explain your codebase again. Let AI remember everything.

🌐 kratos-mcp.com • Installation • Quick Start • Features • Documentation • Contributing

🎯 Why Kratos?

After building 30+ production apps with AI, we discovered a critical problem: AI tools forget everything between sessions. You explain your architecture, your patterns, your decisions—and tomorrow, you explain it all again.

Kratos MCP solves this with the Four Pillars Framework—a battle-tested system that gives AI perfect memory of your project.

✨ Features
🔒 100% Project Isolation

Each project gets its own SQLite database. No cross-contamination. Ever.
🎯 95.8% Context Accuracy

Smart retrieval engine that knows exactly what memories matter for your current task.
⚡ Zero Configuration

Auto-detects projects via git, package.json, or directory structure. Just install and code.
🌍 Universal Protocol

Works with Claude, Cursor, Windsurf, Continue—any MCP-compatible tool.
🚀 Installation
# Install globally
npm install -g kratos-mcp

# Or run directly with npx (no installation required)
npx kratos-mcp

# Or install as a dependency
npm install kratos-mcp
🎬 Quick Start
1️⃣ Configure Your AI Tool
Claude Desktop

Add to your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/claude/claude_desktop_config.json
{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}

Or if you have it installed globally:

{
  "mcpServers": {
    "kratos": {
      "command": "kratos-mcp",
      "args": []
    }
  }
}
Claude Code (Anthropic's VSCode Extension)

Run this command in your terminal:

claude mcp add kratos -- npx --yes kratos-mcp@latest

Or for global installation:

# First install globally
npm install -g kratos-mcp@latest

# Then add to Claude Code
claude mcp add kratos -- kratos-mcp

See Claude Code MCP docs for more info.

Cursor

Add to .cursor/mcp_config.json in your project root:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Windsurf (Codeium)

Add to ~/.windsurf/mcp_config.json:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Cline (VSCode Extension)
  1. Open VSCode Command Palette (Cmd+Shift+P)
  2. Run "Cline: Edit MCP Settings"
  3. Add server configuration:
{
  "kratos": {
    "command": "npx",
    "args": ["kratos-mcp"]
  }
}
BoltAI
  1. Open BoltAI Settings
  2. Navigate to MCP Servers
  3. Add new server with:
{
  "name": "kratos",
  "command": "npx",
  "args": ["kratos-mcp"]
}
Augment Code

Add to Augment settings under MCP configuration:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Roo Code (VSCode Extension)

Add to .roo/config.json:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Zencoder

Configure in Zencoder settings:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Amazon Q Developer

Add to Q Developer settings:

{
  "mcpServers": [
    {
      "name": "kratos",
      "command": "npx",
      "args": ["kratos-mcp"]
    }
  ]
}
Qodo Gen

Add to Qodo configuration:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
JetBrains AI Assistant
  1. Open Settings → Tools → AI Assistant
  2. Add MCP server:
{
  "kratos": {
    "command": "npx",
    "args": ["kratos-mcp"]
  }
}
Warp Terminal

Add to ~/.warp/mcp_config.json:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Opencode

Configure in Opencode settings:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Copilot Coding Agent

Add to Copilot configuration:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Kiro

Add to Kiro settings:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
OpenAI Codex

Configure in Codex settings:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
LM Studio

Add to LM Studio MCP configuration:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Perplexity Desktop

Add to Perplexity settings:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Continue.dev

Add to ~/.continue/config.json:

{
  "models": [...],
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["kratos-mcp"]
    }
  }
}
Zed

Add to ~/.config/zed/settings.json:

{
  "assistant": {
    "mcpServers": {
      "kratos": {
        "command": "npx",
        "args": ["kratos-mcp"]
      }
    }
  }
}
VS Code (Generic MCP Extensions)

For any MCP-compatible VS Code extension, add to .vscode/settings.json:

{
  "mcpServers": {
    "kratos": {
      "command": "npx",
      "args": ["--yes", "kratos-mcp@latest"]
    }
  }
}
Other MCP Tools

Kratos works with any tool supporting the Model Context Protocol. The general format is:

{
  "command": "npx",
  "args": ["kratos-mcp"]
}

Check your tool's documentation for specific MCP server configuration location.

2️⃣ Start Using Kratos
// Your AI now remembers:
// ✓ Your authentication patterns
// ✓ Your API structure  
// ✓ Your component architecture
// ✓ Your coding standards
// ✓ Every decision you've made
🏛️ The Four Pillars Framework

Based on real-world experience building 30+ production apps with AI, Kratos implements the Four Pillars of effective AI development:

📋 Pillar 1: PRD (Product Requirements)

"What Matters"

Define not just what to build, but how AI should build it:

  • Complete page paths and user flows
  • API endpoints and data structures
  • Edge cases and integration points
  • UI/UX references and patterns
🎯 Pillar 2: Prompt Templates

"What to Do"

Reusable task templates that work perfectly with your codebase:

  • Role & stack definition
  • Clear scope constraints
  • File context specifications
  • Verification steps
🧠 Pillar 3: Context Retrieval

"What to Inject"

Smart injection of relevant memories based on your current task:

  • Automatic pattern matching
  • Path-based relevance scoring
  • Recency weighting
  • Semantic clustering
💾 Pillar 4: Memory Storage

"What to Save"

Permanent knowledge base that grows with your project:

  • Architecture decisions
  • Bug fixes and solutions
  • Feature implementations
  • Performance optimizations
🛠️ Core Tools
Tool Description Example
memory_save Store important project knowledge 
// Save authentication pattern
memory_save({
  title: "JWT Auth Flow",
  content: "Tokens in httpOnly cookies...",
  tags: ["auth", "security"]
})
memory_search Retrieve relevant memories 
// Get auth-related memories
memory_search({
  query: "authentication",
  k: 5
})
prd_update Define project requirements 
// Update PRD section
prd_update({
  feature: "api_structure",
  content: "RESTful endpoints..."
})
prompt_build Create reusable prompts 
// Build structured prompt
prompt_build({
  goal: "Create React component",
  role: "Senior React Developer"
})
📊 How It Works
graph LR
    A[Your Code] --> B[Kratos MCP]
    B --> C{Project Detection}
    C --> D[Project Database]
    D --> E[Memory Storage]
    D --> F[Context Broker]
    F --> G[AI Tool]
    G --> H[Perfect Context]
🔬 Under the Hood
  • SQLite + FTS5: Lightning-fast full-text search
  • Smart Scoring: Path matching + recency + importance
  • Auto-detection: Git, package.json, or directory-based
  • Secure: All data stays local, no external calls
📈 Performance
Metric Value
Context Accuracy 95.8%
Memory Retrieval < 10ms
Project Switch < 100ms
Storage Overhead ~2MB per project
🗂️ Memory Structure
.kratos/
├── projects/
│   ├── project-id-1/
│   │   ├── memories.db      # SQLite database
│   │   ├── prd.yml          # Product requirements
│   │   └── prompts/          # Reusable templates
│   └── project-id-2/
│       └── ...
└── config.yml                # Global configuration
🎮 Live Demo
// User: "Explain the auth system"
// 
// Kratos automatically retrieves:
// ✓ JWT implementation from 2 weeks ago
// ✓ Middleware configuration from last month  
// ✓ User model structure from initial setup
// ✓ Security decisions from PRD
//
// AI Response: "Your auth uses JWT with refresh tokens 
// stored in httpOnly cookies. The middleware validates 
// tokens on protected routes at /api/middleware/auth.ts:42..."
🤝 Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

# Clone the repo
git clone https://github.com/ceorkm/kratos-mcp.git

# Install dependencies
npm install

# Run in development
npm run dev
📄 License

MIT © 2025 Kratos MCP Contributors

🙏 Acknowledgments

Built on the Model Context Protocol by Anthropic.

Inspired by the Four Pillars Framework and real-world experience building production apps with AI.

Built for developers who value their time.

Report Bug • Request Feature • Documentation

作者情報
ceorkm
ceorkm
GitHub

1

フォロワー

2

リポジトリ

0

Gist

0

貢献数

タグ
ai-developmentai-toolsclaudecoding-assistantcontext-managementcursordeveloper-toolskratosllmmcpmemory-managementmodel-context-protocolprompt-engineeringsqlitetypescript
関連するMCP
mobile-mcp logo
mobile-mcp
53

Mobile MCPは、モバイルデバイスの自動化機能を提供するMCPサーバーです。構造化されたUIダンプを使用して、LLMがスクリーンショットや視覚的入力に依存せずにモバイルデバイスと対話できるようにします。現在はAndroidデバイスのみがサポートされており、iOSのサポートも予定されています。

TypeScript
mcp-openapi-schema-explorer logo
mcp-openapi-schema-explorer
45

MCP server providing token-efficient access to OpenAPI/Swagger specs via MCP Resources for client-side exploration.

TypeScript
keycloak-model-context-protocol logo
keycloak-model-context-protocol
31

Keycloak MCP Serverは、Keycloakの管理を効率化するためのツールを提供します。ユーザーやレルムの管理が可能で、特定のレルムに新しいユーザーを作成したり、削除したり、利用可能なレルムや特定のレルム内のユーザーを一覧表示する機能があります。これにより、システム管理者はユーザー管理を簡素化できます。

TypeScript