Ontology-based MCP server that analyzes database schemas (PostgreSQL, Snowflake, ClickHouse, Dremio) and generates RDF/OWL ontologies with SQL mappings for fan-trap-free Text-to-SQL.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Claude Desktop
Claude Code
Cursor
Add to claude_desktop_config.json:
{
"mcpServers": {
"orionbelt-analytics": {
"command": "uvx",
"args": [
"orionbelt-analytics"
]
}
}
}📋 Copy
Run in terminal:
claude mcp add orionbelt-analytics uvx orionbelt-analytics📋 Copy
Add to .cursor/mcp.json:
{
"mcpServers": {
"orionbelt-analytics": {
"command": "uvx",
"args": [
"orionbelt-analytics"
]
}
}
}📋 Copy
Or install with pip: pip install orionbelt-analytics
README Excerpt
<!-- mcp-name: io.github.ralfbecher/orionbelt-analytics --> <p align="center"> <img src="https://raw.githubusercontent.com/ralfbecher/orionbelt-analytics/main/assets/ORIONBELT_Logo.png" alt="OrionBelt Logo" width="400"> </p> <h1 align="center">OrionBelt Analytics</h1> <p align="center"><strong>The Ontology-based MCP server for your Text-2-SQL convenience.</strong></p>
Tools (20)
add_rdf_knowledge apply_semantic_names cleanup_workspace connect_database discover_schema download_artifact execute_sql_query generate_chart generate_ontology get_semantic_model get_server_info get_table_details graphrag_find_join_path graphrag_query_context graphrag_search list_schemas list_semantic_models load_my_ontology query_sparql reset_cache
Topics
agentic-ai chromadb claude-desktop clickhouse databricks dremio graphrag knowledge-graph mcp mcp-server model-context-protocol ontology owl postgresql r2rml