Orionbelt Semantic Layer
API-first semantic engine and query planner for AI agents that compiles declarative YAML models into optimized, dialect-specific SQL across BigQuery, PostgreSQL, Snowflake, ClickHouse, Dremio, Databricks, DuckDB, and MySQL.
What is Orionbelt Semantic Layer?
Orionbelt Semantic Layer is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to api-first semantic engine and query planner for ai agents that compiles declarative yaml models into optimized, dialect-specific sql across bigquery, postgresql, snowflake, clickhouse, dremio, databri...
API-first semantic engine and query planner for AI agents that compiles declarative YAML models into optimized, dialect-specific SQL across BigQuery, PostgreSQL, Snowflake, ClickHouse, Dremio, Databricks, DuckDB, and MySQL.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- API-first semantic engine and query planner for AI agents th
Use Cases
Maintainer
Works with
Installation
PIP
pip install orionbelt-semantic-layerManual Installation
pip install orionbelt-semantic-layerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Orionbelt Semantic Layer
OrionBelt Semantic Layer is an API-first semantic engine that compiles declarative YAML models (OBML format) into optimized, dialect-specific SQL across eight databases: BigQuery, ClickHouse, Databricks, Dremio, DuckDB/MotherDuck, MySQL, PostgreSQL, and Snowflake. AI agents connect via the MCP server to translate natural-language questions into structured queries without ever hand-writing SQL. It is designed for data teams who want a single semantic model that powers BI tools, AI assistants, and custom analytics pipelines simultaneously.
Prerequisites
- Python 3.9 or later installed
- pip or uv package manager available
- A running OrionBelt API service (orionbelt-api command or Docker image ralforion/orionbelt-api)
- One or more OBML YAML model files describing your data sources
- An MCP client such as Claude Desktop or Claude Code CLI
Install the package
Install orionbelt-semantic-layer from PyPI. Using uv is preferred for speed, but pip works equally well.
pip install orionbelt-semantic-layer
# or with uv
uv pip install orionbelt-semantic-layerStart the OrionBelt API server
Launch the REST API, which also serves the MCP endpoint. Set MODEL_FILES to a comma-separated list of your OBML model paths so they are pre-loaded at startup.
MODEL_FILES=./models/sales.yaml,./models/inventory.yaml orionbelt-apiEnable query execution (optional)
By default the API only generates SQL. Set QUERY_EXECUTE=true to allow the server to actually run queries against connected databases.
QUERY_EXECUTE=true MODEL_FILES=./models/sales.yaml orionbelt-apiConfigure Claude Desktop
Add the MCP server to your Claude Desktop configuration file. The server communicates via the OrionBelt REST API, so point it at the running instance.
{
"mcpServers": {
"orionbelt": {
"command": "orionbelt-mcp",
"env": {
"API_BASE_URL": "http://localhost:8000"
}
}
}
}Verify the connection
Open Claude Desktop and ask it to list available semantic models. The MCP server should return the models loaded at startup.
Write your first OBML model
Create a YAML file following the OBML schema to define dimensions, measures, and joins for your data object. This model is what the AI agent queries against.
version: "1.0"
dataObjects:
Orders:
code: ORDERS
columns:
Revenue: { code: REVENUE, abstractType: float }
dimensions:
TotalRevenue:
dataObject: Orders
column: RevenueOrionbelt Semantic Layer Examples
Client configuration
Claude Desktop config pointing to a locally running OrionBelt API.
{
"mcpServers": {
"orionbelt": {
"command": "orionbelt-mcp",
"env": {
"API_BASE_URL": "http://localhost:8000",
"QUERY_EXECUTE": "true"
}
}
}
}Prompts to try
Example questions you can ask Claude once OrionBelt is connected.
- "Show me total revenue by region for the last 30 days"
- "Generate a BigQuery SQL query for monthly order counts grouped by product category"
- "What dimensions and measures are available in the sales model?"
- "Run a PromQL-style breakdown of daily revenue for Q1 in Snowflake dialect"Troubleshooting Orionbelt Semantic Layer
orionbelt-mcp command not found after installation
Ensure your Python scripts directory is on PATH. Run 'pip show orionbelt-semantic-layer' to confirm installation, then add the Scripts/bin directory to your PATH environment variable.
API returns 'model not found' errors
Set the MODEL_FILES environment variable to the absolute paths of your OBML YAML files before starting orionbelt-api. Use comma separation for multiple files.
SQL generation succeeds but query execution fails
QUERY_EXECUTE must be set to 'true' and the database connection credentials must be configured in your OBML model file. Check that the target database is reachable from the host running orionbelt-api.
Frequently Asked Questions about Orionbelt Semantic Layer
What is Orionbelt Semantic Layer?
Orionbelt Semantic Layer is a Model Context Protocol (MCP) server that api-first semantic engine and query planner for ai agents that compiles declarative yaml models into optimized, dialect-specific sql across bigquery, postgresql, snowflake, clickhouse, dremio, databricks, duckdb, and mysql. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Orionbelt Semantic Layer?
Install via pip with: pip install orionbelt-semantic-layer. Then configure your AI client to connect to this MCP server.
Which AI clients work with Orionbelt Semantic Layer?
Orionbelt Semantic Layer works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Orionbelt Semantic Layer free to use?
Yes, Orionbelt Semantic Layer is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Orionbelt Semantic Layer Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Orionbelt Semantic Layer? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Orionbelt Semantic Layer in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Orionbelt Semantic Layer?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.