Server facts
orionbelt-semantic-layer-mcp
Project
- Author
- ralfbecher
- License
- Not specified
- Category
- Databases
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 3
- Last commit
- Data as of
Tags
- Semantic Layer
- agentic ai
- business intelligence
- semantic sidecar
Overview
OrionBelt organizes analytical queries around named dimensions, measures, and metrics defined in OBML, its YAML modeling format. Its SQL compilation targets Postgres, Snowflake, ClickHouse, Dremio, and Databricks. For analysts and developers working through AI assistants, the tools expose model structure before query construction: describe_model presents objects and relationships, find_artefacts supports ranked discovery or exact lookup, and explain_artefact traces definitions back to their source columns. Model-authored examples provide query payloads with SQL previews, while get_model retrieves the original YAML in single-model mode.
During query development, find_composables identifies elements compatible with an existing selection and distinguishes combinations involving the Composite Fact Layer. Relationship inspection is available through an adjacency-list join graph and Mermaid ER diagrams. For semantic graph workflows, the model can be retrieved as OBSL-Core RDF in Turtle or inspected through read-only SPARQL SELECT and ASK queries. Published JSON Schemas support local document validation. Finally, execute_query compiles a semantic query and returns both SQL and results, applying a server-side row limit when the query omits one.
orionbelt-semantic-layer-mcp setup notes
- orionbelt-semantic-layer-mcp records stdio only; confirm a network transport upstream before planning remote access.
- orionbelt-semantic-layer-mcp has no recorded license; confirm reuse terms in its repository.