orionbelt-semantic-layer-mcp 1.8.0

Thin MCP server for OrionBelt Semantic Layer — delegates to REST API

OrionBelt Semantic Layer MCP

Thin MCP server that delegates to the OrionBelt Semantic Layer REST API

A thin MCP server that delegates all business logic to the OrionBelt Semantic Layer REST API via HTTP. No embedded engine — pure API pass-through.

Architecture

The OrionBelt Semantic Layer platform has two deployment modes. This MCP server supports both:

• Standalone — Deploy the OrionBelt Semantic Layer API anywhere (Cloud Run, Docker, localhost) and point this MCP server at it via API_BASE_URL.
• Hosted — Use the managed deployment on Prefect Horizon with zero local setup (see Live Demo Hosting below).

┌────────────┐       ┌──────────────────────────────────────────────────────┐
│ LLM Client │       │                OrionBelt Platform                    │
│            │       │                                                      │
│  Claude,   │──MCP──│──> server.py  ──HTTP /v1──>  Semantic Layer REST API │
│  Cursor,   │       │    (FastMCP                   (FastAPI: parse OBML,  │
│  any MCP   │       │     + httpx)                   validate, compile     │
│  client    │       │                                to SQL)               │
└────────────┘       └──────────────────────────────────────────────────────┘

• No business logic — all tool calls delegate to the REST API (v1 endpoints)
• Dual-mode — auto-detects single-model or multi-model API mode at startup
• Auto-session management — creates an API session on first tool call, caches the ID (multi-model mode)
• 22 tools (single-model mode) or 25 tools (multi-model mode) for querying, execution, discovery, diagrams, RDF/SPARQL, and format conversion
• 3 prompts + 1 resource for OBML reference and usage guidance

Live Demo

A public demo of the OrionBelt Semantic Layer API is available at:

API endpoint: http://35.187.174.102 — Swagger UI | ReDoc | Gradio UI

Set API_BASE_URL=http://35.187.174.102 in your .env file to use it (see .env.example).

Installation

uv sync

For development (includes pytest, respx, ruff):

uv sync --all-groups

Usage

stdio (default)

uv run server.py

HTTP transport

MCP_TRANSPORT=http uv run python server.py

MCP client configuration

Add to your MCP client config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "orionbelt": {
      "command": "uv",
      "args": ["run", "python", "server.py"],
      "cwd": "/path/to/orionbelt-semantic-layer-mcp"
    }
  }
}

Configuration

Environment variables or .env file (pydantic-settings). See .env.example for defaults.

Variable	Default	Description
API_BASE_URL	— (required)	OrionBelt Semantic Layer REST API URL
MCP_TRANSPORT	stdio	stdio, http, or sse
MCP_SERVER_HOST	localhost	Bind host for HTTP/SSE
MCP_SERVER_PORT	9000	Bind port for HTTP/SSE
LOG_LEVEL	INFO	Logging level
API_TIMEOUT	30	HTTP timeout in seconds

Tools

Model lifecycle

MCP Tool	Description
get_obml_reference()	Returns the full OBML format specification
load_model(model)	Parse, validate, and store a semantic model (JSON object)
describe_model(model_id)	Inspect data objects, dimensions, measures, metrics
remove_model(model_id)	Remove a model from the current session
list_models()	List all models loaded in the current session

Model discovery

MCP Tool	Description
get_model_schema(model_id)	Full model structure as JSON (detailed)
list_dimensions(model_id)	List all dimensions in a model
get_dimension(model_id, name)	Get a single dimension by name
list_measures(model_id)	List all measures in a model
get_measure(model_id, name)	Get a single measure by name
list_metrics(model_id)	List all metrics in a model
get_metric(model_id, name)	Get a single metric by name
explain_artefact(model_id, name)	Explain lineage of a dimension, measure, or metric
find_artefacts(model_id, query)	Search artefacts by name or synonym
get_join_graph(model_id)	Return the join graph as an adjacency list

Query, execution & diagrams

MCP Tool	Description
compile_query(...)	Compile a semantic query to SQL (with explain plan)
execute_query(...)	Compile and execute a query, returning SQL + result data
get_model_diagram(model_id)	Generate a Mermaid ER diagram for a loaded model

Semantic graph (RDF / SPARQL)

MCP Tool	Description
get_graph(model_id)	Return the model as OBSL-Core RDF (Turtle)
sparql_query(model_id, query)	Run a read-only SPARQL query (SELECT / ASK)

Utilities

MCP Tool	Description
list_dialects()	List available SQL dialects and capabilities
get_settings()	Get API config (single-model mode, TTL, Flight SQL)
convert_osi_to_obml(input_yaml)	Convert OSI YAML to OBML format
convert_obml_to_osi(input_yaml)	Convert OBML YAML to OSI format

Supported SQL Dialects

postgres, snowflake, clickhouse, databricks, dremio, bigquery, duckdb

Workflow

1. Get reference — call get_obml_reference() to learn OBML syntax
2. Load model — call load_model(model_yaml) to get a model_id
3. Explore — call describe_model(model_id) or use discovery tools (list_dimensions, find_artefacts, explain_artefact, etc.)
4. Query — call compile_query(model_id, dimensions=[...], measures=[...]) to generate SQL
5. Execute — call execute_query(model_id, dimensions=[...], measures=[...]) to run SQL and get results (requires QUERY_EXECUTE=true on the API)

Integration Guides

Use the OrionBelt Semantic Layer MCP server with popular AI agent frameworks and automation platforms:

Framework	Transport	Guide
OpenAI Agents SDK	stdio, HTTP, SSE	docs/integrations/openai-agents-sdk.md
LangChain	stdio, HTTP	docs/integrations/langchain.md
Google ADK	stdio, HTTP, SSE	docs/integrations/google-adk.md
n8n	HTTP, SSE	docs/integrations/n8n.md
CrewAI	stdio, HTTP	docs/integrations/crewai.md

Each guide includes quick-start examples, multi-agent patterns, and connection options for both the hosted demo and self-hosted deployments.

Development

# Run tests
uv run pytest

# Lint
uv run ruff check server.py
uv run ruff format server.py tests/

MCP Live Demo Hosting at Prefect Horizon

The OrionBelt Semantic Layer MCP server is available as a hosted live demo on Prefect Horizon, a managed platform for deploying MCP servers.

MCP URL

Use this URL to connect any MCP-compatible client to the hosted server (no authentication required):

https://orionbelt-semantic-layer.fastmcp.app/mcp

Quick start with Claude Desktop

1. Download the Desktop Extension: orionbelt-semantic-layer.dxt
2. Open the .dxt file in Claude Desktop (requires Claude Desktop with MCP support)

No local setup or API key needed — the hosted server connects to the live demo API.

License

Copyright 2025 RALFORION d.o.o.

Licensed under the Apache License, Version 2.0. See LICENSE for details.

---