icon for mcp server

Kratos

STDIO

AI编程工具的记忆系统与项目知识存储

🏛️ Kratos MCP

Ultra-Lean Memory System for AI Coding Tools

npm version License: MIT MCP Compatible TypeScript

Never explain your codebase again. Let AI remember everything.

🌐 kratos-mcp.comInstallationQuick StartFeaturesTools


🎯 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 an ultra-lean memory system that gives AI perfect recall of your project—with minimal context overhead.

✨ Features

🔒 100% Project Isolation

Each project gets its own SQLite database. No cross-contamination. Ever.

Zero Configuration

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

🪶 Ultra-Lean Architecture

Just 12 essential tools. 64% smaller context footprint than competitors.

🌍 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"] } } }
Other MCP Tools

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

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

Compatible with: Windsurf, Cline, BoltAI, Augment Code, Roo Code, Zencoder, Amazon Q, Qodo Gen, JetBrains AI, Warp, Opencode, Continue.dev, Zed, and more!

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

🛠️ Available Tools

Kratos provides 12 ultra-lean tools optimized for minimal context consumption:

💾 Memory Management (7 tools)

ToolDescription
memory_saveStore important project knowledge with tags, paths, and importance levels
memory_searchSmart semantic search with debug mode and path matching
memory_askNatural language queries about your memories
memory_get_recentGet recently created memories with filtering
memory_getRetrieve a specific memory by ID
memory_get_multipleBulk retrieve multiple memories
memory_forgetDelete a memory by ID

🔒 Security (1 tool)

ToolDescription
security_scanScan text for PII and secrets before saving

📁 Project Management (3 tools)

ToolDescription
project_switchSwitch between different projects
project_currentGet current active project info
change_storage_pathDynamically change storage location with automatic data migration

⚙️ System (1 tool)

ToolDescription
system_statusGet system status and memory statistics

📊 How It Works

graph LR A[Your Code] --> B[Kratos MCP] B --> C{Project Detection} C --> D[SQLite Database] D --> E[Memory Storage] E --> F[AI Tool] F --> G[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
  • Lean: Only 4 core components, minimal memory footprint

📈 Performance

MetricValue
Context Overhead64% smaller than v3
Memory Retrieval< 10ms
Project Switch< 100ms
Storage Overhead~2MB per project

🗂️ Memory Structure

~/.kratos/                       # Default storage location
├── projects/
│   ├── project-id-1/
│   │   └── memories.db          # SQLite database with FTS5
│   └── project-id-2/
│       └── memories.db
└── global/
    └── global.db                # Shared knowledge (optional)

New in v1.6.1: Use change_storage_path to move data to custom locations like /opt/kratos or .kratos for per-project storage.

💡 Example Usage

// Save a memory await memory_save({ summary: "JWT auth implementation", text: "We use httpOnly cookies with refresh tokens...", tags: ["auth", "security"], paths: ["src/middleware/auth.ts"], importance: 5 }); // Search memories await memory_search({ q: "authentication", k: 5, debug: true // Get search insights }); // Ask natural language questions await memory_ask({ question: "How does our auth system work?", limit: 10 }); // Change storage location await change_storage_path({ newPath: "/opt/kratos", migrate: true, backup: true });

🎮 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 // // 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 # Build npm run build # Run in development npm run dev

📄 License

MIT © 2025 Kratos MCP Contributors

🙏 Acknowledgments

Built on the Model Context Protocol by Anthropic.

Inspired by real-world experience building production apps with AI.


Built for developers who value their time.

Report BugRequest FeatureDocumentation

MCP Now 重磅来袭,抢先一步体验