Database-agnostic MCP server that exposes relational databases as governed business objects (Customers, Orders, Products) for AI agents via ORM abstraction — instead of raw SQL or schema access. Works with any JDBC-compliant database (PostgreSQL, MySQL, Oracle, SQL Server, SQLite, and more). Reduces LLM token consumption by 60-70% through semantic data abstraction.
概要
ORMCP Server bridges the gap between AI applications and relational databases using the standard MCP protocol. It enables LLMs like Claude, Gemini, and OpenAI GPT to interact with data through semantic, business-object-focused interfaces rather than complex database schemas.
Key Features
- Database-agnostic — works with any JDBC-compliant database (e.g., Oracle, SQL Server, PostgreSQL, MySQL, SQLite)
- ORM-based curated business object abstraction (Customers, Orders, Products)
- Reduces token consumption by 60-70%
- Bi-directional read/write operations
- Optional read-only mode for governed access
- Docker-based deployment via Gilhari microservice
Documentation
サーバー設定
{
"mcpServers": {
"ormcp-server": {
"command": "ormcp-server",
"args": [],
"env": {
"GILHARI_BASE_URL": "http://localhost:80/gilhari/v1/",
"MCP_SERVER_NAME": "ORMCPServer"
}
}
}
}