mcpindex.aiv0
← Index

Nouz

io.github.Semiotronika/NOUZ-MCP·v3.0.3·Memory & RAG
Quality Score
90
/100

Semantic knowledge engine for Obsidian with auto-classification and DAG hierarchy

Repository →
§01  Install
Claude Desktop (uvx)
{
  "mcpServers": {
    "NOUZ-MCP": {
      "command": "uvx",
      "args": [
        "nouz-mcp"
      ],
      "env": {
        "OBSIDIAN_ROOT": "./obsidian",
        "NOUZ_CONFIG": "<nouz_config>",
        "NOUZ_DATABASE_NAME": "obsidian_kb.db",
        "NOUZ_DATABASE_PATH": "<nouz_database_path>",
        "EMBED_ENABLED": "true",
        "EMBED_PROVIDER": "openai",
        "EMBED_MODEL": "<embed_model>",
        "EMBED_API_URL": "http://127.0.0.1:1234/v1"
      }
    }
  }
}
§02  Environment variables
OBSIDIAN_ROOT

Path to Obsidian vault

NOUZ_CONFIG

Absolute path to config.yaml; if omitted, server looks in current working directory

NOUZ_DATABASE_NAME

SQLite cache filename inside OBSIDIAN_ROOT

NOUZ_DATABASE_PATH

Full SQLite cache path; takes precedence over NOUZ_DATABASE_NAME

EMBED_ENABLED

Enable embedding-based features

EMBED_PROVIDER

Embedding provider: openai, gigachat, lmstudio, ollama

EMBED_MODEL

Embedding model name

EMBED_API_URL

Embedding API endpoint

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
15
installability
25
documentation
15
stability
10
§04  Alternatives in Memory & RAG
DoneThat
ai.donethat/donethat

Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.

Fodda Knowledge Graphs
ai.fodda/mcp-server

Expert-curated knowledge graphs for AI agents — PSFK Retail, Beauty, Sports and more.

ai.meminal/meminal
ai.meminal/meminal

Memory for deep conversational context across any platform