mcp-database-tools
# mcp-database-tools
MCP server providing SQL and database tools for AI agents. All analysis is performed on SQL text — no actual database connection required.
## Tools
### sql_format
Format and prettify SQL queries with proper indentation, uppercased keywords, and aligned columns. Supports MySQL, PostgreSQL, and SQLite syntax.
### sql_explain
Take a SQL query and explain what it does in plain English, step by step. Identifies query type, tables, columns, conditions, and provides optimization tips.
### schema_analyze
Parse CREATE TABLE statements to extract tables, columns, types, constraints, foreign keys, and indexes. Generates an ER diagram in Mermaid format.
### query_build
Build SQL queries from natural language descriptions. Supports common patterns like filtering by date, aggregation, joins, ordering, and pagination.
### migration_generate
Compare two schemas (old vs new CREATE TABLE statements) and generate ALTER TABLE migration statements. Produces both up (forward) and down (rollback) migrations.
## Installation
```bash
npm install
npm run build
```
## Usage
### With Claude Desktop
Add to your Claude Desktop config (`claude_desktop_config.json`):
```json
{
"mcpServers": {
"database-tools": {
"command": "node",
"args": ["path/to/mcp-database-tools/dist/index.js"]
}
}
}
```
### Standalone
```bash
npm start
```
## Development
```bash
npm run build # Compile TypeScript
npm start # Run the server
```
## License
MIT
TDQS
Scored across 5 tools
Each tool addresses a distinct aspect of database work: formatting, natural language query building, explaining SQL, schema analysis, and migration generation. No two tools overlap in purpose, making selection unambiguous.
All tool names follow a consistent '<domain>_<action>' pattern (e.g., sql_format, schema_analyze), with noun-first ordering and snake_case throughout. This creates a predictable and readable convention.
With 5 tools, the set is concise and well-scoped for a database utility server. Each tool covers a core workflow (format, build, explain, analyze, migrate) without redundancy or bloat.
The tool set covers the full lifecycle of SQL development: creating/formatting queries, building from natural language, understanding, analyzing schema, and generating schema migrations. No critical gaps are apparent for the stated purpose.