orionbelt-semantic-layer-mcp

<!-- mcp-name: io.github.ralforion/orionbelt-semantic-layer-mcp --> <p align="center"> <img src="https://raw.githubusercontent.com/ralforion/orionbelt-semantic-layer-mcp/main/docs/assets/ORIONBELT_Logo.png" alt="OrionBelt Logo" width="400"> </p> <h1 align="center">OrionBelt Semantic Layer MCP</h1> <p align="center"><strong>Thin MCP server that delegates to the OrionBelt Semantic Layer REST API</strong></p> [](https://github.com/ralforion/orionbelt-semantic-layer-mcp/releases) [](https://github.com/ralforion/orionbelt-semantic-layer) [](https://www.python.org/downloads/) [](https://github.com/ralforion/orionbelt-semantic-layer-mcp/blob/main/LICENSE) [](https://gofastmcp.com) [](https://docs.pydantic.dev) [](https://docs.astral.sh/ruff/) [](https://cloud.google.com/bigquery) [](https://www.postgresql.org) [](https://www.snowflake.com) [](https://clickhouse.com) [](https://www.dremio.com) [](https://www.databricks.com) [](https://duckdb.org) [](https://www.mysql.com) A thin MCP server that delegates all business logic to the [OrionBelt Semantic Layer](https://github.com/ralforion/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](https://github.com/ralforion/orionbelt-semantic-layer) 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](#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](#design-time-vs-run-time-tool-switching)) - **4 prompts + 2 resources** for OBML / OBSQL reference and usage guidance <p align="center"> <img src="https://raw.githubusercontent.com/ralforion/orionbelt-semantic-layer-mcp/main/docs/assets/architecture.png" alt="OrionBelt Analytics Architecture" width="900"> </p> ## Live Demo A public demo of the OrionBelt Semantic Layer API is available at: > **API endpoint:** `https://orionbelt.ralforion.com` — [Swagger UI](https://orionbelt.ralforion.com/docs) | [ReDoc](https://orionbelt.ralforion.com/redoc) | [Gradio UI](https://orionbelt.ralforion.com/ui/?__theme=dark) Set `API_BASE_URL=https://orionbelt.ralforion.com` in your `.env` file to use it (see `.env.example`). ## Installation ```bash uv sync ``` For development (includes pytest, respx, ruff): ```bash uv sync --all-groups ``` ## Usage ### stdio (default) ```bash uv run server.py ``` ### HTTP transport ```bash MCP_TRANSPORT=http uv run python server.py ``` ### MCP client configuration Add to your MCP client config (e.g. `claude_desktop_config.json`): ```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](docs/integrations/openai-agents-sdk.md) | | **LangChain** | stdio, HTTP | [docs/integrations/langchain.md](docs/integrations/langchain.md) | | **Google ADK** | stdio, HTTP, SSE | [docs/integrations/google-adk.md](docs/integrations/google-adk.md) | | **n8n** | HTTP, SSE | [docs/integrations/n8n.md](docs/integrations/n8n.md) | | **CrewAI** | stdio, HTTP | [docs/integrations/crewai.md](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 ```bash # 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`](https://www.npmjs.com/package/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: ```json { "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): ```json { "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`](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](#installation) section above and the [`Dockerfile`](Dockerfile). ## License Copyright 2025 [RALFORION d.o.o.](https://ralforion.com) Licensed under the Apache License, Version 2.0. See [LICENSE](LICENSE) for details. --- <p align="center"> <a href="https://ralforion.com"> <img src="https://raw.githubusercontent.com/ralforion/orionbelt-semantic-layer-mcp/main/docs/assets/RALFORION_doo_Logo.png" alt="RALFORION d.o.o." width="200"> </a> </p>