orionbelt-semantic-layer-mcp 2.17.0

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 — 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)
• 15 tools (single-model mode) or 19 tools (multi-model mode) for querying (QueryObject), execution, batch, discovery, composability (ACR), examples, diagrams, RDF/SPARQL, OSI export, and OBML reference + JSON schemas. (20 distinct tools exist in total; the API mode selects which subset is active — they overlap in 14 — and no client ever sees all 20 at once.) The visible surface is narrowed further in the design-time phase and when query execution is disabled (see Design-time vs run-time tool switching)
• 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
API_KEY	— (unset)	API credential; required only when the API runs with AUTH_MODE=api_key
API_KEY_HEADER	X-API-Key	Header the credential is sent in; must match the API's API_KEY_HEADER
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? | osi_yaml?, dedup=True)	Parse, validate, and store a model (returns health + model_load). Pass model (OBML JSON) or osi_yaml (OSI YAML, converted to OBML server-side)
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
export_model_to_osi(model_id, ...)	Export a loaded model as OSI YAML

Model discovery

MCP Tool	Description
find_artefacts(model_id, query?, kind?, name?)	Look up artefacts. With query → fuzzy, ranked search (resolve a vague term: exact / synonym / fuzzy). Without query → exact, deterministic lookup (all artefacts, one kind, or one named artefact, full records)
explain_artefact(model_id, name)	Explain lineage of a dimension, measure, or metric
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
find_composables(query_json?, anchors?, anchor_type?, model_id?)	ACR — given an in-progress query or named anchor(s), return the dimensions/measures/metrics that still compose into a valid, fanout-free result (plus CFL candidates). Guaranteed to compile

Query, execution & diagrams

MCP Tool	Description
execute_query(...)	Compile and execute a QueryObject, returning SQL + rows
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_model_graph(model_id)	Return the model as OBSL-Core RDF (Turtle)
query_model_graph_by_sparql(query, ...)	Run a read-only SPARQL query (SELECT / ASK)

References

MCP Tool	Description
get_obml_reference()	OBML (model authoring) grammar reference
get_json_schema(name)	JSON Schema for obml (model) or query (QueryObject)

Utilities

MCP Tool	Description
list_dialects()	List available SQL dialects and capabilities

Design-time vs run-time tool switching

The server presents a phase-scoped tool surface: instead of listing all all tools at once, it shows only the tools that make sense for where you are in the model lifecycle. About half the tools are meaningless until a model is loaded (execute_query, describe_model, find_artefacts, …) and the rest are about authoring or reference (get_obml_reference, get_json_schema, list_dialects). Splitting them keeps the surface small and prevents a whole class of error — calling a query tool with no model loaded.

Three buckets, swapped by phase

Tools fall into three buckets. The visible surface is a swap at the load/unload transition, not additive — the run phase does not show the design/reference tools:

Bucket	Listed when	Tools
Always	always (both phases)	load_model, remove_model (transition verbs — stay available in the run phase so a second model can be loaded mid-session, up to max_models_per_session); run_batch (self-contained one-shot — loads/references a model inline, so it needs no prior session state); get_json_schema (QueryObject/OBML schemas — needed in both phases)
Design-only	only when no model loaded	get_obml_reference, list_dialects
Run-only	only when a model is loaded	describe_model, get_model_diagram, find_artefacts, explain_artefact, execute_query, list_examples, get_example, get_model_graph, get_join_graph, find_composables, query_model_graph_by_sparql, list_models, export_model_to_osi

                       load_model  (returns "re-list" signal)
   ┌─────────────────┐ ────────────────────────────────▶ ┌───────────────┐
   │ design phase    │                                   │ run phase     │
   │ always + design │ ◀───────────────────────────────  │ always + run  │
   └─────────────────┘  remove_model (last model) / TTL  └───────────────┘
                        expiry — back to design phase

So design phase → always + design-only, run phase → always + run-only. Design/reference tools are hidden once a model is loaded, keeping the run surface focused on querying.

Re-listing

The MCP tools/list response is filtered to the active phase. Because the stateless MCP spec makes push notifications (notifications/tools/list_changed) unreliable, transitions are pull-based: load_model (design → run) and remove_model (run → design, once no models remain) return a short signal telling the client to re-list its tools and pick up the swapped surface.

Guard against premature calls

If a client calls a run-only verb while still in the design phase (e.g. a stale host that hasn't re-listed yet), the server returns a structured error rather than an opaque failure:

No model loaded — 'execute_query' is a run-time tool and is not available yet. Call load_model first, then re-list tools.

Capability gating (orthogonal to phase)

Separately from lifecycle phase, a tool can be hidden because the server is configured not to support it. The execution tool execute_query is gated on the API's query_execute capability: when the server runs compile-only it is dropped from tools/list and calling it returns a structured error. This composes with phase — a verb is listed only if its phase is active and its capability is enabled. The mechanism is a general capability registry, so future "the server can't do X here" flags hide their tools the same way.

Single-model mode

When the API runs in single-model mode a model is pre-loaded at startup, so the server is permanently in the run-time phase — every applicable tool is listed from the first request and there is no load_model step.

Note on caching hints. The 2026-07-28 MCP spec adds ttlMs / cacheScope hints on tools/list (SEP-2549). These are intentionally not set yet — the fields are a release candidate, and FastMCP's list-tools hook exposes only the tool list, not the result envelope. The explicit re-list signal above is the primary (and spec-recommended) transition mechanism in the meantime.

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 (find_artefacts, explain_artefact)
4. Execute — call execute_query(model_id, query_json='{"select": {"dimensions": [...], "measures": [...]}}') to compile and run SQL, returning rows (requires QUERY_EXECUTE=true on the API; see get_json_schema("query") for the QueryObject shape)

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 and format
uv run ruff check server.py
uv run ruff format server.py tests/

# Set up pre-commit hooks (recommended)
./scripts/setup-hooks.sh

Release Process

The release script (scripts/release.sh) includes comprehensive pre-flight checks to prevent issues like the v2.8.2 formatting problem:

• Code formatting check - Ensures ruff format passes
• Linting check - Ensures ruff check passes
• CI status check - Warns if CI is not green
• Test suite - Runs all tests
• Version consistency - Verifies version across files
• Changelog - Ensures changelog entry exists

Pre-commit hooks are available to catch issues early. Run ./scripts/setup-hooks.sh to install them.

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.

---