Foggy Data MCP BridgeAI-Native Semantic Layer Framework

Enable AI assistants to query business data safely and accurately through MCP protocol

中文文档

English Docs

GitHub

🔒

Security First

DSL-based queries eliminate SQL injection risks. Field-level access control with read-only design.

🎯

Model-as-Code

Define data models using FSScript (JavaScript-like syntax). Functions, imports, and dynamic logic.

🌐

Multi-Database

MySQL, PostgreSQL, SQL Server, SQLite, MongoDB - same DSL works everywhere.

🤖

AI-Native MCP

Native MCP protocol support. Out-of-box integration with Claude Desktop & Cursor.

📊

Auto Visualization

Automatic chart generation - trend charts, bar charts, pie charts, and more.

🚀

Production Ready

Spring Boot based, Docker support, bilingual docs, extensible addon system.

Why This Project?

❌ The Problem: Letting AI Write SQL Directly is Dangerous

Problem	Impact
Security Risks	AI may generate `DELETE`, `UPDATE`, or access sensitive tables
Schema Exposure	Must share complete database schema with AI
No Business Semantics	What does `order_status=3` mean? AI doesn't know
Complex JOINs	Multi-table relationships and aggregations are fragile

✅ Our Solution: Semantic Layer with DSL Query Language

AI → JSON DSL Query → Semantic Layer → Safe SQL → Database
                            ↓
                    • Prevents SQL injection
                    • Enforces access control
                    • Handles multi-table JOINs
                    • Abstracts database dialects

📦 Core Modules

Module	Description
foggy-dataset-model	Semantic layer engine - TM/QM modeling, DSL query execution
foggy-dataset	Database abstraction - MySQL, PostgreSQL, SQL Server, SQLite
foggy-fsscript	Script engine - JavaScript-like syntax for TM/QM files
foggy-dataset-mcp	MCP server - AI assistant integration