SQL Generative MCP
Enables natural language querying of PostgreSQL databases under read-only mode, returning results as structured XML.
README
SQL Generative MCP
An interactive Model Context Protocol (MCP) server that translates plain English queries into SQLAlchemy operations, queries a PostgreSQL database under strict read-only execution modes, and returns the query results formatted as structured XML.
🌟 Key Features
- Natural Language DB Querying: Translate user queries in plain English to corresponding database results dynamically.
- SQLAlchemy Table Reflection: Reflects database schemas dynamically across multiple namespaces using standard ORM capabilities (no direct
pg_dumpclient tools needed). - Enforced Read-Only Transactions: Database URL connections are injected with query options (
?options=-c%20default_transaction_read_only%3Don) to natively block any modifications (CREATE,UPDATE,DELETE,DROP) at the database engine level. - Dynamic XML Response Formatting: Converts database records into a clean, well-formed XML structure automatically compiled by Claude.
- FastMCP Protocol Integration: Built on top of the standard
fastmcpSDK to run as a local stdio MCP server.
🏗️ Architecture

🛠️ Setup & Installation
Prerequisites
- Python 3.13+
- uv (fast Python package installer and resolver)
- PostgreSQL Server with an active database
1. Project Initialization & Dependencies
Initialize the project environment and install dependencies:
uv sync
2. Environment Configuration
Create a .env file in the root directory and configure the database URL along with your Anthropic API key:
# Database connection for local development (enforced read-only mode via query options)
DATABASE_URL=postgresql://postgres:admin@localhost:5432/expence_db?options=-c%20default_transaction_read_only%3Don
# Anthropic API Key
ANTHROPIC_API_KEY="your-anthropic-api-key-here"
🚀 Running the Server
Start the stdio-based MCP server locally:
uv run python main.py
🔌 Integration with Claude Desktop
To configure Claude Desktop to use this database query tool on Windows, configure your claude_desktop_config.json file.
- Press
Win + R, type%APPDATA%\Claudeand press Enter. - Open
claude_desktop_config.jsonand insert the following server config:
{
"mcpServers": {
"db-query-server": {
"command": "uv",
"args": [
"--directory",
"c:/Projects/generative-tool",
"run",
"python",
"main.py"
]
}
}
}
- Restart Claude Desktop. You will see the tools icon 🔌 in the chat input area.
📈 Usage Examples
Once connected, you can ask Claude queries like:
- "Show a list of all tables in the database"
- "How many expense entries are recorded for AWS?"
- "Show a list of all rows in table exp_expence_core_t"
The server returns results formatted as well-formed XML:
<data>
<item>
<exp_expence_core_id>26</exp_expence_core_id>
<title>AWS Bill</title>
<amount>100.00</amount>
</item>
</data>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。