DatI MCP server lets AI agents discover database semantics and run pre-configured parameterized SQL operations securely across connected databases.
Search tables, column definitions, and business semantic terms across DatI-connected databases (read-only).
Resolve NL2SQL schema ambiguity and understand domain-specific abbreviations before querying.
Execute published parameterized SQL tools by specifying service_code, tool_name, and JSON-encoded params.
Run specific business database operations; these may read or mutate data depending on the configured SQL template (INSERT/UPDATE/DELETE).
Use DatI row-level permission guards and SQL parameter binding for safer execution.
Access databases such as MySQL, PostgreSQL, ClickHouse, and Doris through published MCP services.
Allows connecting to ClickHouse analytical databases, with tools for metadata inspection and SQL execution so AI agents can query analytical data.
Allows connecting to MySQL relational databases, exposing metadata inspection and SQL execution tools for querying and updating data.
Allows connecting to PostgreSQL relational databases, exposing metadata inspection and SQL execution tools for querying and updating data.
DatI (Data Intelligence) is a lightweight semantic gateway connecting AI Agents with enterprise databases. Simply connect your database, enrich semantic metadata, and configure built-in or parameterized SQL tools to publish an MCP service — ready for your agents or any MCP host.
┌────────────────────┐ ┌────────────────────┐ ┌────────────────────┐
│ User A: OpenCode │ │ User B: WorkBuddy │ │ User N: DataAgent │
└──────────┬─────────┘ └──────────┬─────────┘ └──────────┬─────────┘
└───────────────────────┼───────────────────────┘
▼ MCP (Streamable HTTP)
┌─────────────────────────────── DatI ───────────────────────────────┐
│ Semantic │ Security │ Tools │
└──────────────────────────────────┬─────────────────────────────────┘
▼
┌────────────────────────────────────────────────────────────────────┐
│ MySQL │ PostgreSQL │ ClickHouse │ Doris │
└────────────────────────────────────────────────────────────────────┘Demo URL: https://dati-demo.zhangyimin.me
The demo instance is preloaded with sample data and reset periodically.
Data and configuration reference the AdventureWorks sample and can be automated via the dati-ops skill.
Related MCP server: foggy-odoo-bridge
git clone https://github.com/yimindev/dati.git && cd dati
cp .env.example .env # Configure JWT_SECRET and ES password
docker compose up -dOpen http://localhost:8085. Register with username admin to get super admin role. For production tuning and external DB setup, see Deployment Guide.
Multi-Database Support: Supports MySQL, PostgreSQL, ClickHouse, Doris, and other relational and analytical databases
Semantic Enhancement: Supports business terms, column aliases, and automatic enum dictionary extraction. Combined with semantic search, it helps models understand business jargon and find the right tables
Flexible Integration: Based on standard MCP (Streamable HTTP), easily integrates into your existing agents or workflows
Effortless MCP Publishing: Ready-to-use built-in tools (schema inspection, SQL execution) and parameterized SQL tools to publish MCP services with zero extra deployment
Security & Governance: Centrally managed database credentials with user-level permission and data scope isolation
Conversational Data Analysis (NL2SQL): Connect business databases and support NL2SQL analysis workflows with semantic metadata and built-in tools
Lightweight App Development: Wrap databases as MCP services so agents can query and update data through conversation to build lightweight applications
Backend: Spring Boot 3.5.x + Java 21 + JPA
Frontend: Vue 3 + TypeScript + Vite + Element Plus + TailwindCSS 4
Database: H2 (Development) / MySQL / PostgreSQL (Production)
Search Engine: Elasticsearch (Semantic Retrieval)
Local Development Guide: Environment setup, backend/frontend startup, and project conventions
Server Deployment Guide: Architecture overview, Docker Compose deployment, and operational maintenance
Architecture Overview: High-level architecture, module index, and key design conventions
Examples:
Enterprise BI & Retail Analytics (AdventureWorks DW): Star schema Text-to-SQL, metric governance, multi-table joins, and parameterized acceleration
Family Finance Assistant: Multi-user collaborative bookkeeping, parameterized permission control, transparent SQL queries, and self-healing agent workflows
Agent Skills (Agent Skills Open Standard, auto-discovered by repository agents):
dati-ops: User Skill — Configure and operate the platform via HTTP APIs (data sources, subjects & terms, MCP services); self-contained with built-in openapi.json and query tools, independently distributable; connected in-repo via .agents/skills/dati-ops/
e2e-tester: Developer Skill — E2E HTTP integration tests and API behavior validation (see test cases in e2e-tests/test-cases/)
User Guide: docs/user-guide (VitePress site, bilingual)
API Specification: docs/api/openapi.json (Used by E2E test toolchains)
AI Coding Assistant Guidelines: AGENTS.md and .agents/rules/ (Backend, frontend, and design system rules)
Articles: DEV.to Series (DatI Devlog)
Discussions: LINUX DO
WeChat Official Account:
Execute a pre-configured parameterized SQL tool published on the DatI MCP gateway.
Behavior: - May mutate data depending on the configured SQL template (INSERT/UPDATE/DELETE). - Safe execution: Protected by DatI row-level permission guards and SQL parameter binding. Usage Guidelines: - Use this tool when you need to run specific business database operations. - Prerequisite: Use search_metadata first if you are unsure of the service or parameters.
Inputs: tool_name (required), service_code (required), params. Returns: result
Search tables, column definitions, and business semantic terms across databases connected to DatI.
Behavior: - Read-only: Safe to call anytime with no side effects or destructive actions. Usage Guidelines: - Call this tool FIRST to discover existing tables, columns, and business terms before invoking execute_parameterized_sql. - Suitable for resolving NL2SQL schema ambiguity and understanding domain-specific abbreviations.
Inputs: query (required). Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: search_metadata is read-only discovery of schemas and terms, while execute_parameterized_sql runs a pre-configured SQL operation. There is no meaningful overlap or risk of misselection.
Both names use consistent snake_case with a verb-first pattern: search_metadata and execute_parameterized_sql. The convention is predictable and readable.
Only two tools are provided, which feels thin even for a focused MCP gateway. A minimal search-and-execute pair can work, but the surface is borderline and lacks supporting operations.
Metadata search and parameterized execution cover the core loop, but there is no explicit tool to discover the available parameterized SQL services or their parameters. This notable gap may force agents to rely on implicit knowledge.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Governed MCP gateway for business apps: roles, previews, approvals and one audit log.
One governed MCP endpoint for 40+ business systems. Read-only, source-cited answers.
Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data.
