Kratos MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kratos MCP remember that our authentication uses JWT"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Kratos MCP
Ultra-Lean Memory System for AI Coding Tools
Never explain your codebase again. Let AI remember everything.
Kratos has evolved. This repo is now legacy.
github.com/ceorkm/kratos-cli
Kratos is now a standalone CLI — faster, lighter, works with ANY AI agent.
No MCP overhead. No vendor lock-in. Just memory that works.
npx kratos-memoryClaude Code, Codex, Cursor, Cline — anything that runs Bash.
Your existing memories work instantly. Same ~/.kratos/ storage, same SQLite format.
Go to Kratos CLI >
Related MCP server: mcp-memento
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-mcpQuick Start
1. Configure Your AI Tool
Add to your Claude Desktop config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.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": []
}
}
}Run this command in your terminal:
claude mcp add kratos -- npx --yes kratos-mcp@latestOr for global installation:
# First install globally
npm install -g kratos-mcp@latest
# Then add to Claude Code
claude mcp add kratos -- kratos-mcpAdd to .cursor/mcp_config.json in your project root:
{
"mcpServers": {
"kratos": {
"command": "npx",
"args": ["--yes", "kratos-mcp@latest"]
}
}
}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.
2. Start Using Kratos
// Your AI now remembers:
// - Your authentication patterns
// - Your API structure
// - Your component architecture
// - Your coding standards
// - Every decision you've madeAvailable Tools
Kratos provides 12 ultra-lean tools optimized for minimal context consumption:
Memory Management (7 tools)
Tool | Description |
| Store important project knowledge with tags, paths, and importance levels |
| Smart semantic search with debug mode and path matching |
| Natural language queries about your memories |
| Get recently created memories with filtering |
| Retrieve a specific memory by ID |
| Bulk retrieve multiple memories |
| Delete a memory by ID |
Security (1 tool)
Tool | Description |
| Scan text for PII and secrets before saving |
Project Management (3 tools)
Tool | Description |
| Switch between different projects |
| Get current active project info |
| Dynamically change storage location with automatic data migration |
System (1 tool)
Tool | Description |
| Get system status and memory statistics |
How It Works
AI Tool ──► Kratos MCP ──► Project Detection ──► SQLite + FTS5 ──► Perfect ContextSQLite + 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
Metric | Value |
Context Overhead | 64% smaller than v3 |
Memory Retrieval | < 10ms |
Project Switch | < 100ms |
Storage Overhead | ~2MB per project |
Data Storage
~/.kratos/
├── projects/
│ ├── project-id-1/
│ │ └── memories.db # SQLite database with FTS5
│ └── project-id-2/
│ └── memories.db
└── global/
└── global.db # Shared knowledge (optional)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
});
// Ask natural language questions
await memory_ask({
question: "How does our auth system work?",
limit: 10
});Contributing
git clone https://github.com/ceorkm/kratos-mcp.git
npm install
npm run build
npm run devLicense
MIT
Built for developers who value their time.
Available Tools
12 toolschange_storage_pathB
Dynamically change where Kratos stores data (with automatic migration)
Inputs: newPath (required), migrate, backup.
memory_askC
Ask questions about your memories using natural language
Inputs: question (required), limit.
memory_forgetB
Delete a memory by ID
Inputs: id (required).
memory_getB
Get a specific memory by ID with full text
Inputs: id (required).
memory_get_multipleB
Get multiple memories by IDs with full text (bulk operation)
Inputs: ids (required).
memory_get_recentB
Get recent memories from active project
Inputs: k, path_prefix, include_expired.
memory_saveC
Save a memory document to the active project
Inputs: summary (required), text (required), tags, paths, +2 more.
memory_searchC
Search memory documents in the active project
Inputs: q (required), k, require_path_match, tags, +3 more.
project_currentA
Get current active project
Inputs: no named parameters.
project_switchC
Switch to a different project
Inputs: project_path (required).
security_scanB
Scan text for PII and secrets
Inputs: text (required), redact.
system_statusA
Get system status and statistics
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Most tools have distinct purposes, but memory_get and memory_get_multiple are closely related, and memory_ask could be conflated with memory_search if not careful. Overall, boundaries are clear.
All tool names follow a consistent verb_noun pattern in snake_case, making them predictable and easy to navigate.
With 12 tools, the set is well-scoped for a memory and project management system, neither too sparse nor overwhelming.
Missing a memory update tool and project listing capability. The set covers core CRUD for memories but lacks lifecycle operations for projects and explicit memory updates.
Maintenance
Related MCP Connectors
Shared memory for coding agents. Stop re-explaining your codebase every session.
Project memory, documentation and controlled secret access for AI coding agents.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Project memory for coding agents: requirements, decisions, code graph and delivery telemetry.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides AI coding assistants with persistent project memory to retain architectural decisions, code patterns, and domain knowledge across sessions. It stores data locally in a SQLite database, allowing agents to remember, recall, and manage project-specific context using full-text search.3 npmApache 2.0
- AlicenseAqualityBmaintenanceProvides AI coding assistants with persistent memory storage using a local SQLite database. Enables tools to remember project details, notes, and relationships across sessions to maintain context and reduce repetitive explanations.174MIT
- AlicenseAqualityBmaintenanceLocal-first memory for AI coding agents using SQLite, enabling persistent recall of decisions, lessons, and project context without cloud or API keys.10105 PyPI291Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides a local long-term memory layer for AI coding tools like Cursor and Claude Code, enabling cross-session, cross-tool sharing of project facts, user preferences, decisions, and workflows.11 npm2MIT