MCP.so
登录

SQLGenius - AI-Powered SQL Assistant MCP Server

@pawankumar94

基本信息

分类

数据库

传输方式

stdio

作者

pawankumar94

关于 SQLGenius - AI-Powered SQL Assistant MCP Server

SQLGenius is an AI-powered SQL assistant that converts natural language to SQL queries using Vertex AI's Gemini Pro. Built with MCP and Streamlit, it provides an intuitive interface for BigQuery data exploration with real-time visualization and schema management.

SQLGenius - AI-Powered SQL Assistant MCP Server 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块,请前往代码仓库查看安装说明。

代码仓库

SQLGenius - AI-Powered SQL Assistant MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is SQLGenius?

SQLGenius is an intelligent SQL assistant that helps you query your BigQuery database using natural language. Built with MCP, Vertex AI's Gemini Pro, and Streamlit, it is designed for data analysts and developers who want to interact with their data conversationally.

How to use SQLGenius?

Clone the repository, install dependencies, copy the .env.example to .env, and fill in your BigQuery project and credential details. Start the application with streamlit run streamlit_app.py; the MCP server launches automatically. Use the Streamlit UI tabs to ask natural language questions, write SQL queries directly, or explore your database schema.

Key features of SQLGenius

  • Natural language to SQL conversion using Gemini Pro
  • Interactive Streamlit UI with multiple tabs
  • Real-time query execution and visualization
  • Database schema explorer
  • Query history tracking
  • Safe query validation (only SELECT permitted)

Use cases of SQLGenius

  • Ask questions about your data in plain English, e.g., "Show me the top 5 customers by revenue"
  • Write and execute raw SQL queries directly against BigQuery
  • Browse available tables, view schemas, and see sample data
  • Track and revisit previously run queries

常见问题

1

What MCP tools does SQLGenius expose?

It provides four tools: `execute_nl_query` (natural language query), `execute_sql_query` (raw SQL), `list_tables` (list all tables), and `get_table_schema` (schema for a specific table).

2

What security restrictions apply?

Only SELECT queries are permitted. Query validation prevents dangerous operations, and error handling with input validation is included.

3

What are the runtime dependencies?

Python, the packages listed in `requirements.txt`, a Google BigQuery project (PROJECT_ID, DATASET_ID), a service account JSON key, and a Vertex AI location (default `us-central1`).

4

How do I start the MCP server?

The MCP server starts automatically when you launch the Streamlit app via `streamlit run streamlit_app.py`.

5

Can I add custom tools?

Yes. Edit the `register_tools()` method in `sql_mcp_server.py`, add your tool using the `@self.tool()` decorator, and restart the server.

评论

数据库 分类下的更多 MCP 服务器