data-ai MCP Server
Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory
Discovered via github-topic:mcp-server and last synced 3mo ago.
1. Install the package
npx claude-soul init --starter
2. Add to claude_desktop_config.json
{
"mcpServers": {
"claude-soul-monorepo": {
"command": "npx",
"args": [
"claude-soul-monorepo"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
~20 signals
Read soul files (SOUL.md, SHADOW.md, etc.)
Load identity + frameworks + state at session start
</details> <details> <summary><b>Data files</b></summary>
Trigger
Record a self-evaluation of a complex response
25-100 signals
Manual or auto
Purpose
Select relevant frameworks for current conversation
Load a single framework with full evidence history
Record observed interaction patterns
Trigger a reflection cycle (quick/deep/meta)
Write to user-editable soul files
Get current system status
Purpose
What it does
Save facts, decisions, or lessons
Semantic search across all memories
Search or browse conversation journals
List recently saved memories
Memory system statistics
Unified "ask anything about the past" search