What databases does Database MCP Server support?
It supports SQLite, PostgreSQL, MySQL/MariaDB, and SQL Server.
@georgi-terziyski
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"database_mcp_server": {
"command": "python",
"args": [
"-m",
"db_mcp_server"
]
}
}
}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。
Database MCP Server is a Model Context Protocol (MCP) server that provides a unified interface for connecting to and interacting with multiple database systems: SQLite, PostgreSQL, MySQL/MariaDB, and SQL Server. It is designed for LLMs like Claude to execute queries, manage schemas, and handle transactions programmatically.
Install from source with pip install -e ., configure via environment variables (DB_CONFIG_PATH, DB_CONNECTIONS) or a JSON config file, then run as an MCP server with python -m db_mcp_server or as a standalone web server with python -m db_mcp_server.web_server. Use built-in MCP tools like execute_query, list_tables, or add_connection. For other LLMs, send HTTP POST requests to the /call_tool endpoint.
It supports SQLite, PostgreSQL, MySQL/MariaDB, and SQL Server.
Connections are configured via environment variables (`DB_CONFIG_PATH`, `DB_CONNECTIONS`) or a JSON configuration file specifying type, host, port, credentials, and database path.
Python 3.8+ and SQLAlchemy are required, along with optional database‑specific drivers like `psycopg2-binary` (PostgreSQL) or `mysql-connector-python` (MySQL).
It supports the standard MCP protocol (stdio) and can also run as a standalone HTTP web server exposing `/list_tools` and `/call_tool` endpoints.
Data resides in the connected external databases; the server itself does not store any data.
A MCP (model context protocol) server that gives the LLM access to and knowledge about relational databases like SQLite, Postgresql, MySQL & MariaDB, Oracle, and MS-SQL.
An official Qdrant Model Context Protocol (MCP) server implementation
Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.
评论