What is SmartDB_MCP CLAUDE.md?

A project guide for SmartDB, a server that lets software connect to and operate on different databases through the Model Context Protocol, a standard way for AI tools to call external services. It documents setup, startup commands, supported databases, and the project structure.

Use it when working on SmartDB, including database connections, authentication, health checks, SQL optimisation, indexes, or local and Docker startup.

It gives a coding agent the repository rules and commands it needs before changing or running the project. It also explains how to start the server in different connection modes.

How wenb1n-dev/SmartDB_MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to wenb1n-dev/SmartDB_MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/wenb1n-dev/SmartDB_MCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/wenb1n-dev/SmartDB_MCP

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wenb1n-dev/smartdb_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/wenb1n-dev/smartdb_mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/wenb1n-dev/smartdb_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wenb1n-dev/smartdb_mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/wenb1n-dev/smartdb_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wenb1n-dev/smartdb_mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,168 This file is loaded in full into every session.

When invoked 3,168 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.03168	$0.03168
Opus 5.5	$0.01267	$0.01267
Sonnet 5.5	$0.00634	$0.00634
Haiku 4.5	$0.00317	$0.00317

Measured 15d ago against content hash bfeeb46ac0d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SmartDB_MCP CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

SmartDB 是一个通用数据库网关，实现 MCP (Model Context Protocol) 服务器接口，允许 MCP 客户端连接并操作多种数据库。除基础连接探索外，还提供 OAuth 2.0 认证、健康检查、SQL 优化、索引健康检测等高级功能。

支持数据库：MySQL、PostgreSQL、Oracle、SQL Server、达梦 (DM8)、Redis (KV)、MongoDB (文档)、Milvus (向量)。

Common Commands

依赖安装

uv sync

本地启动 (默认 streamable_http 模式，监听 0.0.0.0:3000)

uv run -m core.server
uv run -m core.server --mode sse
uv run -m core.server --mode stdio
uv run -m core.server --envfile /path/to/.env
uv run -m core.server --oauth=true   # 仅 streamable_http 模式支持

Docker

docker-compose up -d
docker-compose logs -f smartdb
docker build -t smartdb-mcp:latest .

pip 包入口

安装后通过 smartdb 命令启动（见 pyproject.toml 中的 [project.scripts]）。

测试

仓库当前未配置测试框架或测试用例。新增功能时如需测试，请先与用户确认测试方案。

Architecture

整体分层

src/core/server.py        — MCP 服务器入口（stdio / sse / streamable_http 三种模式）
src/tools/                — MCP 工具层（每个工具对外暴露给 MCP 客户端）
src/databases/            — 数据库操作抽象工厂层（按数据库类型分目录）
src/connection/           — 连接池管理（SQLAlchemy QueuePool，多库单例）
src/config/               — 配置加载（database_config.json + .env）
src/oauth/                — OAuth 2.0 认证（JWT + 密码模式 + refresh_token）
src/utils/                — SQL 执行与权限校验工具
src/static/login/         — Vue 构建产物（OAuth 登录页，勿手改）

启动流程 (core/server.py:main)

load_dotenv 加载 .env（默认 src/config/.env，可由 --envfile 覆盖）
MultiDBPoolManager.init_from_config() 初始化所有连接池（单例，整个进程共享）
根据 --mode 选择 run_stdio / run_sse / run_streamable_http
streamable_http 模式下，若 --oauth=true，挂载 OAuthMiddleware、/login、/mcp/authorize 路由及静态文件

关键设计模式

1. 工具自动注册（src/tools/base.py + src/tools/init.py）

ToolsBase 子类在 __init_subclass__ 中自动调用 ToolRegistry.register(cls)，无需手动注册
tools/__init__.py 动态扫描目录下所有 .py 模块并导入以触发注册；新增工具文件放入 src/tools/ 即可被自动发现，类名需以 Tool 结尾
server.py 通过 ToolRegistry.get_all_tools() 向 MCP 客户端暴露工具列表

Read the full file on GitHub · 188 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

15d ago First seen · 188 lines · 3,168 tokens per session scan A bfeeb46ac0d7

Subscribe to this mod's changes

SmartDB_MCP CLAUDE.md is an instructions file published in the GitHub repository wenb1n-dev/SmartDB_MCP (78 stars, last pushed 14d ago), licensed MIT. It adds 3,168 tokens to every session, about $0.0127 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-23.

Backend and APIs Databases mcp mcp-server mysql oauth2 oracle postgresql

SmartDB_MCP CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
SmartDB_MCP CLAUDE.mdwenb1n-dev/SmartDB_MCP	Instructions file	78	14d ago	MIT	A	3,168	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

SmartDB_MCP: Instructions file for Claude Code