# orionbelt-analytics

Analyzes relational database schemas and builds RDF/OWL ontologies with SQL mappings. Use it to explore a schema or check generated SQL against its structure.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 53
- Author: ralforion
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ralforion/orionbelt-analytics
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/orionbelt-analytics

## What it does

The server connects to PostgreSQL, MySQL, Snowflake, ClickHouse, Dremio, BigQuery, DuckDB/MotherDuck, and Databricks SQL. It creates an RDF/OWL ontology, while GraphRAG helps locate tables and columns by meaning. OBQC checks SQL against that ontology, catching issues such as invalid table or column references, bad joins, and fan-traps. It checks structure, not whether a query answers the intended business question.

SPARQL 1.1 queries run through a persistent Oxigraph store. Plotly charts can be rendered with MCP-UI in Claude Desktop. The install command uses `uvx`, and Python 3.13+ is required. Multilingual schema search depends on the configured embedding model.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add orionbelt-analytics -- uvx orionbelt-analytics
```
uvx runs the command named after the package; if the README names another one, use uvx --from orionbelt-analytics <command>

### Codex

**Platform CLI**
```bash
codex mcp add orionbelt-analytics -- uvx orionbelt-analytics
```
uvx runs the command named after the package; if the README names another one, use uvx --from orionbelt-analytics <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "orionbelt-analytics": {
            "command": "uvx",
            "args": [
                "orionbelt-analytics"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from orionbelt-analytics <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "orionbelt-analytics": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "orionbelt-analytics"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from orionbelt-analytics <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add orionbelt-analytics uvx orionbelt-analytics
```
uvx runs the command named after the package; if the README names another one, use uvx --from orionbelt-analytics <command>

## When to use it
- inspect a connected relational database schema
- generate an RDF/OWL ontology with SQL mappings
- find relevant tables and columns by meaning
- validate SQL references and join structure
- visualize query results with charts

## Example prompts
- Analyze the connected database schema and create an RDF/OWL ontology.
- Find the tables and columns relevant to a revenue query.
- Check this SQL for invalid joins and fan-traps.

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27669
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49845

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md