OrionBelt Semantic Layer MCP

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

Version 2.7.2 OrionBelt Semantic Layer 2.7 Python 3.12+ License: Apache 2.0 FastMCP Pydantic v2 Ruff

BigQuery PostgreSQL Snowflake ClickHouse Dremio Databricks DuckDB MySQL

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 — Connect to the public Cloud Run deployment with zero local setup (see Hosted MCP Server 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)
• 30–32 tools (single-model mode) or 33–35 tools (multi-model mode) for querying (QueryObject + OBSQL natural SQL), execution, batch, planning, discovery, examples, diagrams, RDF/SPARQL, freshness cache, reference docs, and format conversion (execute tools add +2 when QUERY_EXECUTE=true)
• 4 prompts + 2 resources for OBML / OBSQL reference and usage guidance

Live Demo

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

API endpoint: https://orionbelt.ralforion.com — Swagger UI | ReDoc | Gradio UI

Set API_BASE_URL=https://orionbelt.ralforion.com 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
HEARTBEAT_AUTH_TOKEN	—	Bearer token forwarded to POST /v1/heartbeat (must match the API's value)

Tools

Model lifecycle

MCP Tool	Description
get_obml_reference()	Returns the full OBML format specification
load_model(model, dedup=True)	Parse, validate, and store a model (returns health + model_load)
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 (exact / synonym / fuzzy buckets)
list_examples(model_id, intent?)	List authored example queries (filterable by intent tag)
get_example(model_id, name)	Get one example with query + compiled SQL preview
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 (QueryObject) to SQL
execute_query(...)	Compile and execute a QueryObject, returning SQL + rows
compile_obsql(model_id, sql, ...)	Compile an OBSQL (natural SQL) query to SQL
execute_obsql(model_id, sql, ...)	Compile and execute an OBSQL query, returning SQL + rows
plan_query(model_id, ...)	Planner view (no SQL); optional warehouse EXPLAIN
run_batch(queries, ...)	One-shot: load a model + run N queries in parallel
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)

Freshness cache

MCP Tool	Description
get_cache_stats()	Cache backend, entry count, hit rate, sweep time
heartbeat(database, schema, table, ts?)	Notify the API a table refreshed (invalidates cache)

References

MCP Tool	Description
get_obml_reference()	OBML (model authoring) grammar reference
get_obsql_reference()	OBSQL (natural SQL surface) grammar reference
list_references()	Index of all references published by the API
get_json_schema(name)	JSON Schema for obml (model) or query (QueryObject)

Utilities

MCP Tool	Description
list_dialects()	List available SQL dialects and capabilities
get_settings()	Get API config (modes, TTL, oneshot batch limits)
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/

Hosted MCP Server

A public hosted instance of this MCP server runs on Google Cloud Run, connected to the live OrionBelt Semantic Layer demo API. No local install, no API key.

Endpoint

https://orionbelt.ralforion.com/mcp

Streamable HTTP (MCP spec 2025-03-26). Stateful — clients should send the initialize handshake and reuse the returned Mcp-Session-Id header.

Quick start with Claude Desktop

Claude Desktop's config schema accepts only stdio launchers — for a remote MCP server, use the mcp-remote stdio↔HTTP bridge (auto-fetched by npx, no manual install).

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) and add:

{
  "mcpServers": {
    "orionbelt": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://orionbelt.ralforion.com/mcp",
        "--transport",
        "http"
      ]
    }
  }
}

Fully quit Claude Desktop (⌘Q on macOS — closing the window isn't enough) and reopen. The OrionBelt tools then appear in the tools menu.

Alternatively, in newer Claude Desktop builds: Settings → Connectors → Add custom connector, paste the URL above. No file editing or npx required.

Why mcp-remote? Claude Desktop's claude_desktop_config.json schema currently only validates stdio entries (command + args). A bare {"url": "…"} entry is rejected with "not valid MCP server configurations and were skipped". mcp-remote runs a local stdio bridge that forwards to the HTTPS endpoint, so Claude Desktop sees a normal stdio server. Claude Code does support {"type": "url", "url": "…"} natively — see below.

Quick start with Claude Code

Add to .mcp.json in any repo (or ~/.config/claude-code/.mcp.json globally):

{
  "mcpServers": {
    "orionbelt": {
      "type": "url",
      "url": "https://orionbelt.ralforion.com/mcp"
    }
  }
}

Other MCP clients

Any client that supports Streamable HTTP transport (MCP spec 2025-03-26) can point at the URL above. The endpoint accepts POST /mcp with Accept: application/json, text/event-stream. See tests/cloudrun/test_mcp_cloudrun.sh for a stdlib-only Python smoke test that walks the full handshake.

Notes

• The hosted instance scales to zero when idle, so the first request after a cold period takes ~1–2 seconds longer.
• It connects to the public demo API at https://orionbelt.ralforion.com — same data, same dialects, no authentication. Don't load production data through it.
• For self-hosting, see the Installation section above and the Dockerfile.

License

Copyright 2025 RALFORION d.o.o.

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

---