orionbelt-analytics

概述

OrionBelt Analytics是一个全面的MCP服务器，将关系数据库模式转换为带有嵌入式SQL映射的RDF/OWL本体。它支持多种数据库系统，包括PostgreSQL、Snowflake、ClickHouse、Dremio、BigQuery、DuckDB、Databricks和MySQL。该服务器提供具有自动风扇陷阱预防的关系感知文本转SQL功能、用于智能模式发现的GraphRAG以及交互式图表功能。其主要功能是OBQC（基于本体的查询检查），这是一个确定性SQL验证器，可在查询到达数据库之前捕获结构错误。

试试问 AI

装完之后，这里有 5 个你可以让 AI 做的事：

• connect_database

  Connect to any supported database using .env credentials

  试试:Connect to PostgreSQL database试试:Connect to Snowflake warehouse
• list_schemas

  List available schemas in the connected database

  试试:Show all schemas in the database试试:List available schemas
• discover_schema

  Analyze schema structure with automatic GraphRAG + ontology generation

  试试:Discover schema for public schema试试:Analyze database structure
• get_table_details

  Get detailed column, key, and constraint info for a specific table

  试试:Show details for customers table试试:Get schema for orders table
• generate_ontology

  Generate RDF/OWL ontology from schema with SQL mapping annotations

  试试:Generate ontology for current schema试试:Create OWL model from database
• suggest_semantic_names

  Detect abbreviations and cryptic names for business-friendly renaming

  试试:Suggest better names for columns试试:Find cryptic identifiers to rename
• sample_table_data

  Preview table data with row limit and injection protection

  试试:Show first 10 rows of products试试:Sample data from sales table
• execute_sql_query

  Execute SQL with OBQC validation, security checks, and fan-trap detection

  试试:Run SELECT query with validation试试:Execute sales analysis query
• generate_chart

  Generate Plotly charts (bar, line, scatter, heatmap) with MCP-UI rendering

  试试:Create bar chart of monthly sales试试:Generate line chart of user growth
• graphrag_search

  Semantic search + schema overview (auto-initialized by discover_schema)

  试试:Search for customer-related tables试试:Find all tables with order data
• graphrag_find_join_path

  Discover join paths between tables via graph traversal

  试试:Find path between customers and orders试试:Show join path between products and sales
• query_sparql

  Execute SPARQL queries (SELECT, ASK, CONSTRUCT — auto-detected)

  试试:Query ontology for all customers试试:Find all product categories in RDF store

可对比工具

安装

git clone https://github.com/ralfbecher/orionbelt-analytics
cd orionbelt-analytics
uv sync

cp .env.template .env

uv run server.py

{
  "mcpServers": {
    "OrionBelt-Analytics": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:9000/mcp",
        "--transport",
        "http-only"
      ]
    }
  }
}

FAQ

OrionBelt Analytics支持哪些数据库？

OrionBelt Analytics支持PostgreSQL、MySQL、Snowflake、ClickHouse、Dremio、BigQuery、DuckDB/MotherDuck和Databricks SQL。

OBQC是如何工作的？

OBQC（基于本体的查询检查）是一个确定性验证器，它在查询执行前将SQL与加载的RDF/OWL本体进行解析，以检查表/列存在性、连接有效性、类型兼容性、聚合正确性和风扇陷阱。

orionbelt-analytics 对比