NOUZ MCP Server

NOUZ MCP Server

MCP Server for local knowledge management. Semantic + keywords + tags

Category
Visit Server

README

NOUZ — MCP Server for local knowledge management

v2.1.0

Install

pip install -r requirements.txt

Run

export OBSIDIAN_ROOT=./obsidian
export EMBED_PROVIDER=ollama  # openai, gigachat
python server.py

Config

Edit config.yaml:

Field Type Description
mode string luca / prizma / sloi
levels dict core=1, pattern=2, module=3, quant=4, artifact=5
thresholds.semantic_bridge_threshold float 0.55 default
etalons list Core signs with text for embedding
prizma_modes dict Keywords per thinking style

Tools

Basic

  • read_file(path) — read note with YAML frontmatter
  • write_file(path, content, metadata) — write note with YAML
  • list_files(level, sign, tags, subfolder) — filter files
  • index_all(with_embeddings) — index to DB
  • embed(text) — get embedding

Navigation

  • get_parents(path) — files linking to this file
  • get_children(path) — files this file links to

Semantics (prizma / sloi)

  • calibrate_cores() — recalculate etalon embeddings
  • recalc_signs() — recalculate sign_auto
  • recalc_core_mix() — recalculate core_mix
  • suggest_metadata(path) — suggest level/sign
  • suggest_parents(path) — suggest links by embeddings
  • format_entity_compact(path) — entity formula

Modes

Mode Level Strict Semantics Description
luca ❌ ❌ Simple graph
prizma ❌ ✅ Semantic bridges + core_mix
sloi ✅ ✅ Strict 5-level hierarchy

File Format

---
level: 2
sign: Ψ
tags: [systems]
---
# Content here

Env Vars

Variable Default Description
OBSIDIAN_ROOT ./obsidian Vault path
EMBED_PROVIDER openai openai / gigachat / ollama
EMBED_API_URL http://127.0.0.1:1234/v1 API endpoint
EMBED_MODEL — Model name
EMBED_API_KEY — API key

Copyright (c) 2026 KVANTRA. MIT License.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured