Metadata-Version: 2.4
Name: nouz-mcp
Version: 3.2.5
Summary: MCP server for Obsidian — semantic knowledge graph with auto-classification, DAG hierarchy, and cross-domain bridge detection
Author-email: Semiotronika <belkinamariaigorevna@yandex.ru>
License-Expression: MIT
Project-URL: Homepage, https://semiotronika.ru
Project-URL: Repository, https://github.com/Semiotronika/NOUZ-MCP
Project-URL: Documentation, https://github.com/Semiotronika/NOUZ-MCP#readme
Project-URL: Changelog, https://github.com/Semiotronika/NOUZ-MCP/blob/main/CHANGELOG.md
Project-URL: Bug Tracker, https://github.com/Semiotronika/NOUZ-MCP/issues
Keywords: mcp,obsidian,knowledge-graph,semantic-classification,rag,llm,notes,pkm,embeddings,dag
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
Classifier: Topic :: Text Processing :: Markup :: Markdown
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: mcp>=1.0.0
Requires-Dist: aiofiles>=23.0.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: aiohttp>=3.9.0
Requires-Dist: aiosqlite>=0.19.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Dynamic: license-file

# NOUZ — Semantic MCP Server for Your Knowledge Base

> *Structure emerges from content.*

Works with Obsidian, Logseq, and any directory of Markdown files.

[![MIT License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://python.org)
[![MCP](https://img.shields.io/badge/protocol-MCP_stdio-lightgrey.svg)](https://modelcontextprotocol.io)
[![PyPI](https://img.shields.io/badge/pypi-nouz--mcp-orange.svg)](https://pypi.org/project/nouz-mcp/)

🇷🇺 [Русская версия](README.md)

---

## Why NOUZ

NOUZ sits between your note base and an AI agent. It helps turn scattered Markdown files into a graph that is useful both to you and to the agent:

1. **Automatic classification (semantics)**
   You define "cores" — the base domains of your knowledge base. When you add a new note, NOUZ reads its text, compares vectors, and proposes a domain sign or a combination of domains.

2. **Connection discovery between notes**
   The server builds a directed structural graph: `hierarchy` is kept as an acyclic DAG, while additional semantic links live alongside it:
   - *Semantic bridges:* two notes from different domains point to the same idea.
   - Explicit tag links can be stored manually in YAML.

3. **Base evolution tracking (drift)**
   NOUZ stores the domain profile of content nodes and can compare it with the declared sign. If a module is described as one domain while its profile gradually pulls toward another, the server shows the divergence (`core_drift`).

Depending on your needs, NOUZ works in three modes: from a simple graph (**LUCA**) to a strict 5-level hierarchy (**SLOI**).

---

## How It Works

1. You describe domains in `config.yaml`: what each domain covers and which textual signals identify it.
2. The server turns those descriptions into vector etalons (locally, via LM Studio or Ollama).
3. Each new note is projected onto those axes. The sign is determined by content, or by you.

One boundary matters here. `artifact_signs` describe the form of L5 artifacts: log, source, hypothesis, specification, and so on. These signs do not roll up into the L4 domain sign. A log stays a log; a source stays a source.

`core_mix` is not a sum of artifact types. It is a domain profile stored in the SQLite index. L4/L3/L2 get it from their own text during `recalc_signs`; parent nodes can then receive an averaged profile from child content nodes through `recalc_core_mix`. `core_drift` appears when the stored domain profile and the current `sign` point to different leading domains.

**Semantic bridges** find connections between notes from different domains when texts are close in meaning. If both notes already have chunks, the bridge is additionally checked against the best chunk pair and returns concrete evidence. Tags remain explicit user metadata.

---

## Quick Start

```bash
pip install nouz-mcp
OBSIDIAN_ROOT=/path/to/vault nouz-mcp
```

Without `config.yaml`, the server starts in **LUCA** mode: graph without semantics, ready immediately.

To enable semantic mode, create a local config from the template:

```bash
cp config.template.yaml config.yaml
```

On Windows PowerShell:

```powershell
Copy-Item config.template.yaml config.yaml
```

Or from source:

```bash
git clone https://github.com/Semiotronika/NOUZ-MCP
cd NOUZ-MCP
pip install -r requirements.txt
cp config.template.yaml config.yaml
OBSIDIAN_ROOT=./vault python server.py
```

Connect to Claude Desktop, Cursor, OpenCode, or any MCP client:

```json
{
  "mcpServers": {
    "nouz": {
      "command": "nouz-mcp",
      "env": {
        "OBSIDIAN_ROOT": "/path/to/vault",
        "NOUZ_CONFIG": "/absolute/path/to/config.yaml",
        "EMBED_API_URL": "http://127.0.0.1:1234/v1"
      }
    }
  }
}
```

---

## MCP Tools

| Tool | Purpose |
|------------|-------|
| `suggest_metadata` | Sign, level, bridges, drift warnings |
| `write_file` | Write a note with YAML frontmatter |
| `update_metadata` | Update YAML only, preserving the note body |
| `read_file` | Read a note + metadata |
| `calibrate_cores` | Update core reference vectors |
| `recalc_signs` | Recalculate signs for all notes |
| `recalc_core_mix` | Recalculate parent domain profiles from child content nodes |
| `index_all` | Re-index the whole base; in PRIZMA/SLOI, `with_embeddings=true` also refreshes file/chunk embeddings |
| `embed` | Get a vector for text in PRIZMA/SLOI |
| `chunk_text` | Split Markdown text into stable chunks in PRIZMA/SLOI |
| `chunk_file` | Split one note body into stable chunks in PRIZMA/SLOI |
| `search_chunks` | Search stored chunk embeddings in PRIZMA/SLOI; by default, reduces anisotropy |
| `list_files` | List files with filters by level and sign |
| `get_children` | Traverse down the graph |
| `get_parents` | Traverse up the graph |
| `suggest_parents` | Find parents for an orphan |
| `add_entity` | Create an entity in one step: automatic sign and hierarchy, explicit tags only |
| `process_orphans` | Auto-fill files without enough markup |

---

## Configuration

Minimal `config.yaml`:

```yaml
mode: prizma

etalons:
  - sign: S
    name: Systems Analysis
    text: >
      Methodology for analysing complex objects: feedback loops,
      emergent properties, self-regulation, bifurcation points.
      Cybernetics, synergetics, dissipative structures, catastrophe
      theory, autopoiesis — tools for understanding how the whole
      exceeds the sum of its parts. Not data and not code — a way
      of thinking about how parts form a whole and why systems
      behave non-linearly.
  - sign: D
    name: Data & Science
    text: >
      Physics and cosmology: from subatomic particles to the large-scale
      structure of the Universe. Lagrangians, curvature tensors, scattering
      cross-sections, quarks, bosons, fermions, plasma, vacuum fluctuations,
      cosmic microwave background, cosmological constant, decoherence.
      Pure science about the nature of matter, energy and spacetime.
  - sign: E
    name: Engineering
    text: >
      Software engineering, machine learning and infrastructure: writing
      and debugging code, deployment, containerisation, neural networks,
      inference, tokenisation, data serialisation, microservices, CI/CD,
      automated testing, refactoring, Git, Docker, Kubernetes, APIs.
      The practical discipline of building computational systems from
      architecture to production.

thresholds:
  sign_spread: 0.05
  confident_spread: 60.0
  pattern_second_sign_threshold: 30.0
  semantic_bridge_threshold: 0.55
  parent_link_threshold: 0.55

artifact_signs:
  - sign: n
    name: Note
    text: Short note, observation, fragment.
  - sign: c
    name: Concept
    text: Definition, concept, entity description.
  - sign: r
    name: Reference
    text: External source, documentation, link, citation.
  - sign: l
    name: Log
    text: Session log, chronology, dialogue record.
  - sign: u
    name: Update
    text: Update, release note, changelog entry.
  - sign: h
    name: Hypothesis
    text: Hypothesis, assumption, speculative idea.
  - sign: s
    name: Specification
    text: Technical specification, instruction, requirements.
```

After setup, run `calibrate_cores`: the server creates reference vectors.
Check pairwise cosines: mean-centered values between different domains should be noticeably lower than raw values. If all pairs are roughly the same, strengthen the differences in the texts.
You can also run the standalone etalon check from the installed package:
`nouz-calc-etalons --config config.yaml`.

`etalons` are semantic domains compared through embeddings.
`artifact_signs` describe the material type of L5 artifacts: note, concept, reference, log, update, hypothesis, or specification. This is a heuristic label. Domains usually use uppercase signs (`S/D/E`), while material types use lowercase signs (`n/c/r/l/u/h/s`); you can replace them in config with any short, non-conflicting values. If needed, add `keywords` to any material type, and the server will use your words for the heuristic instead of the built-in RU/EN set.

### Real Calculation Example

Here are actual results for the S/D/E etalons using the `text-embedding-granite-embedding-278m-multilingual` model:

```text
=== Pairwise Cosine (raw) ===
S↔D: 0.5894    S↔E: 0.5862    D↔E: 0.6022

=== Pairwise Cosine (mean-centered) ===
S↔D: -0.5059   S↔E: -0.5117   D↔E: -0.4822
```

Negative mean-centered values are a good result here: after subtracting the mean vector, domains are well-separated. Current `nouz-calc-etalons` etalon smoke test: S→99.6%, D→98.5%, E→98.1%. This is not a whole-base quality score; it checks that each etalon returns to its own sign after the same centering step.

| Variable | Default | Description |
| --- | --- | --- |
| `OBSIDIAN_ROOT` | `./obsidian` | Path to the vault |
| `NOUZ_CONFIG` | *(empty)* | Absolute path to `config.yaml`; if omitted, the server looks in the current working directory |
| `NOUZ_DATABASE_NAME` | `obsidian_kb.db` | SQLite cache filename inside `OBSIDIAN_ROOT`; useful for isolated checks, for example `obsidian_kb.public.db` |
| `NOUZ_DATABASE_PATH` | *(empty)* | Full SQLite cache path; takes precedence over `NOUZ_DATABASE_NAME` |
| `EMBED_PROVIDER` | `openai` | `openai`, `lmstudio`, `ollama` |
| `EMBED_API_URL` | `http://127.0.0.1:1234/v1` | Embedding endpoint |
| `EMBED_API_KEY` | *(empty)* | API key, if needed |
| `EMBED_MODEL` | *(empty)* | Model name |

---

## Privacy

| Component | Local? |
|-----------|-----------|
| Embeddings (LM Studio / Ollama) | Yes |
| Your notes | Yes |
| NOUZ server | Yes |
| AI agent context (Claude, ChatGPT) | Goes to the cloud |

Everything critical stays on your machine.

---

## Development

```bash
git clone https://github.com/Semiotronika/NOUZ-MCP
cd NOUZ-MCP
pip install -e .
python -m compileall -q nouz_mcp pytest_smoke.py scripts
python -m pytest -q
python test_server.py
```

---

## Links

- 🌐 [semiotronika.ru](https://semiotronika.ru)
- 📦 [PyPI](https://pypi.org/project/nouz-mcp/)
- 🗂️ [Glama Registry](https://glama.ai/mcp/servers/Semiotronika/NOUZ-MCP)
- 🐙 [GitHub](https://github.com/Semiotronika/NOUZ-MCP)

MIT License © 2026 Semiotronika

*Cosines are computed. Syntax changes. Semantics remains.*

<!-- mcp-name: io.github.Semiotronika/NOUZ-MCP -->
