orionbelt-analytics — Claude Code MCP server: schema analysis
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.
claude mcp add orionbelt-analytics -- uvx orionbelt-analyticsWhat orionbelt-analytics 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.
What it helps with
- 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 for the agent
- 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.
How to install orionbelt-analytics
Platform CLI
claude mcp add orionbelt-analytics -- uvx orionbelt-analyticsuvx runs the command named after the package; if the README names another one, use uvx --from orionbelt-analytics <command>
Platform CLI
codex mcp add orionbelt-analytics -- uvx orionbelt-analyticsuvx runs the command named after the package; if the README names another one, use uvx --from orionbelt-analytics <command>
Config file
{
"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>
Config file
{
"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>
Platform CLI
gemini mcp add orionbelt-analytics uvx orionbelt-analyticsuvx runs the command named after the package; if the README names another one, use uvx --from orionbelt-analytics <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about orionbelt-analytics
How do I install orionbelt-analytics in Claude Code?
Run claude mcp add orionbelt-analytics -- uvx orionbelt-analytics. Python 3.13+ is required.
What does orionbelt-analytics do?
It analyzes relational database schemas and creates RDF/OWL ontologies with SQL mappings. It also supports schema discovery and ontology-based SQL checks.
Which databases can orionbelt-analytics connect to?
It supports PostgreSQL, MySQL, Snowflake, ClickHouse, Dremio, BigQuery, DuckDB/MotherDuck, and Databricks SQL.
