by Anarkh-Lee · MCP Server · ★ 936
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is universal-db-mcp safe to install? View the security audit →
Universal DB MCP Connect AI to Your Database with Natural Language A universal database connector implementing the Model Context Protocol (MCP) and HTTP API, enabling AI assistants to query and analyze your databases using natural language. Works with Claude Desktop, Cursor, Windsurf, VS Code, ChatGPT, and 50+ other platforms. Features • Quick Start • <a href="#-suppor
npm install -g universal-db-mcp
npx universal-db-mcpTaken from the project's README on GitHub. Check the security audit before running it.
No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 936 |
| Forks | 91 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 64.650666258248/100 |
| Open Issues | 11 |
| Last Updated | 2026-03-17 |
| Created | 2026-01-23 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~236k |
Explore other popular mcp server tools:
universal-db-mcp is 通用数据库 MCP 连接器：支持 MySQL、PostgreSQL、Oracle、MongoDB 等 17 种数据库，支持 Claude Desktop、Cursor、Windsurf、VS Code、ChatGPT 等 50+ 平台，用自然语言查询和分析数据. It is categorized as a MCP Server with 936 GitHub stars.
universal-db-mcp is primarily written in TypeScript.
The README on GitHub (github.com/Anarkh-Lee/universal-db-mcp) gives: npm install -g universal-db-mcp , then npx universal-db-mcp. Usage details are in the same README.
universal-db-mcp is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: