MCP Database Manager
Enables LLM agents to perform CRUD operations across multiple databases including PostgreSQL, MySQL, and SQL Server using SQLAlchemy. It features configurable permission management and secure connection handling with automatic password redaction.
README
MCP Database Manager
An MCP server that enables LLM agents to perform CRUD operations across multiple databases.
Features
- Multi-Database Support
- Permission Management (Read-only by default)
- SQLAlchemy Integration
list_connectionsredacts passwords from connection URLs in its output
Database Support
This MCP server supports multiple databases. You can enable specific database drivers using installation extras:
| Extra | Database | Drivers Installed |
|---|---|---|
postgres |
PostgreSQL | psycopg2-binary |
mysql |
MySQL | pymysql, cryptography |
mssql |
SQL Server | pymssql |
all |
All of the above | All drivers |
Configuration
The configuration file is located at:
~/.mcp-database-manager/config.yaml(on all platforms)
Example config.yaml:
connections:
- name: "main_db"
url: "sqlite:///./main.db"
readonly: true
Cursor Configuration
To use this MCP server in Cursor, add the following to your MCP settings (Settings > Features > MCP):
Option 1: Local Development (Recommended for debugging)
Use this if you have the source code locally and want to test changes immediately.
{
"mcpServers": {
"database-manager": {
"command": "uv",
"args": [
"run",
"--extra",
"all",
"mcp-database-manager"
],
"cwd": "/absolute/path/to/mcp-database-manager"
}
}
}
Note: Replace
/absolute/path/to/mcp-database-managerwith the actual path to your project directory.
Option 2: Using PyPI (Published version)
Use this to run the stable version published on PyPI without cloning the repository.
{
"mcpServers": {
"database-manager": {
"command": "uvx",
"args": [
"--from",
"mcp-database-manager[all]",
"mcp-database-manager"
]
}
}
}
Troubleshooting
If you see "Module not found" errors, ensure you are using uv run which handles the virtual environment automatically.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.