OrionBelt Semantic Layer is an API-first semantic engine that compiles and executes YAML semantic models as optimized SQL across multiple database dialects. It allows users to query using business concepts instead of raw SQL.
From the registry: API-first semantic layer MCP server compiling YAML models into dialect-specific SQL

$ pip install uvhttps://docs.astral.sh/uv/$ git clone https://github.com/ralfbecher/orionbelt-semantic-layer && cd orionbelt-semantic-layer && uv sync && uv run orionbelt-apihttps://github.com/ralfbecher/orionbelt-semantic-layerPlease install the `orionbelt-semantic-layer` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.12+ and uv** — Required to run the REST API backend that the MCP server delegates to Run: `pip install uv` (https://docs.astral.sh/uv/)
- **Clone and start the REST API** — Clone repo, run uv sync, then start the API server Run: `git clone https://github.com/ralfbecher/orionbelt-semantic-layer && cd orionbelt-semantic-layer && uv sync && uv run orionbelt-api` (https://github.com/ralfbecher/orionbelt-semantic-layer)
Canonical MCP server config (HTTP transport):
- url: `http://localhost:8000`
Note: The MCP server is a separate thin client in orionbelt-semantic-layer-mcp repo that delegates to the REST API. REST API must be running first. Docker Hub: ralforion/orionbelt-api. Hosted demo at http://35.187.174.102. BSL 1.1 license.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.