Integrates with DBeaver to provide access to 200+ database types through existing DBeaver connections, allowing database querying, schema exploration, and data export functionality without additional configuration.
Provides access to MySQL databases for schema exploration and query execution through existing DBeaver connections.
Enables running queries on PostgreSQL databases through DBeaver connections, with support for data retrieval and manipulation operations.
DBeaver MCP Server
A Model Context Protocol (MCP) server that integrates with DBeaver to provide AI assistants access to 200+ database types through DBeaver's existing connections. This MCP server is designed to be production-ready and feature-complete for real-world usage with Claude, Cursor, and other MCP-compatible AI assistants.
🚀 Features
- Universal Database Support: Works with all 200+ database types supported by DBeaver
- Zero Configuration: Uses your existing DBeaver connections
- Secure: Leverages DBeaver's credential management
- Cross-Platform: Works on Windows, macOS, and Linux
- Production Ready: Full error handling, logging, and safety checks
- Resource Support: Browse table schemas through MCP resources
- Business Insights: Track and store analysis insights with tagging
- Multiple Export Formats: CSV, JSON export capabilities
- Schema Management: Complete DDL operations (CREATE, ALTER, DROP)
- Safety First: Built-in query validation and confirmation prompts
🛠️ Available Tools
Tool | Description | Safety Level |
---|---|---|
list_connections | List all DBeaver database connections | ✅ Safe |
get_connection_info | Get detailed connection information | ✅ Safe |
execute_query | Execute SELECT queries (read-only) | ✅ Safe |
write_query | Execute INSERT, UPDATE, DELETE queries | ⚠️ Modifies data |
create_table | Create new database tables | ⚠️ Schema changes |
alter_table | Modify existing table schemas | ⚠️ Schema changes |
drop_table | Remove tables (requires confirmation) | ❌ Destructive |
get_table_schema | Get detailed table schema information | ✅ Safe |
list_tables | List all tables and views in database | ✅ Safe |
export_data | Export query results to CSV/JSON | ✅ Safe |
test_connection | Test database connectivity | ✅ Safe |
get_database_stats | Get database statistics and info | ✅ Safe |
append_insight | Add business insights to memo | ✅ Safe |
list_insights | List stored business insights | ✅ Safe |
📋 Prerequisites
- Node.js 18+
- DBeaver installed and configured with at least one connection
- Claude Desktop, Cursor, or another MCP-compatible client
🛠️ Installation
See the Installation Guide for full details.
Quick Start
🖥️ Configuration
See the Configuration Guide for Claude Desktop and environment variable options.
Claude Desktop Configuration
💡 Usage Examples
Basic Operations
- List connections: "Show me all my database connections"
- Execute query: "Run this query on my PostgreSQL database: SELECT COUNT(*) FROM orders WHERE date > '2024-01-01'"
- Get schema: "What's the schema of the users table in my MySQL database?"
- Export data: "Export all customer data to CSV from my Oracle database"
Advanced Operations
- Schema management: "Create a new table called 'products' with columns id, name, price"
- Data analysis: "Find the top 10 customers by order value and save this insight"
- Safety checks: "I want to drop the test_table - make sure to confirm first"
Business Intelligence
- Track insights: "The Q4 sales data shows a 23% increase in mobile orders - tag this as 'quarterly-analysis'"
- Review analysis: "Show me all insights related to sales performance"
🔧 Resource Browsing
The server provides MCP resources for browsing database schemas:
- Browse table schemas directly in your MCP client
- Resources are automatically discovered from your DBeaver connections
- Provides structured schema information in JSON format
🛡️ Safety Features
- Query Validation: Automatic detection of dangerous operations
- Confirmation Requirements: Destructive operations require explicit confirmation
- Connection Validation: All connections are verified before operations
- Error Handling: Comprehensive error messages and logging
- Rate Limiting: Built-in timeouts to prevent runaway queries
🚀 Production Features
- Comprehensive Logging: Debug mode for troubleshooting
- Error Recovery: Graceful handling of connection failures
- Performance Monitoring: Query execution time tracking
- Business Context: Insight tracking for data analysis workflows
- Multi-format Export: Support for CSV and JSON export formats
🛠️ Scripts
scripts/build.sh
: Build the projectscripts/install.sh
: Install dependencies and build
📝 Documentation
🔄 Comparison with Other MCP Servers
This DBeaver MCP server provides:
- ✅ Universal database support (200+ databases vs. 4-5 in most MCP servers)
- ✅ Resource-based schema browsing
- ✅ Business insights tracking
- ✅ Complete DDL operations (CREATE, ALTER, DROP)
- ✅ Advanced safety features
- ✅ Multiple export formats
- ✅ Production-ready error handling
- ✅ Cross-platform compatibility
🤝 Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/new-feature
- Make your changes and add tests if applicable
- Commit your changes:
git commit -m 'Add new feature'
- Push to the branch:
git push origin feature/new-feature
- Submit a pull request
📝 License
MIT License - see LICENSE file for details
🙏 Acknowledgments
- Anthropic for the Model Context Protocol
- DBeaver for the amazing database tool
- The open source community for inspiration and feedback
Note: This project is not officially affiliated with DBeaver or Anthropic. It's designed for real-world production use with AI assistants.
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
A Model Context Protocol server that enables AI assistants to access and query 200+ database types through existing DBeaver connections without additional configuration.
Related MCP Servers
- -securityFlicense-qualityA Model Context Protocol server that enables AI models to interact with MySQL databases through natural language, supporting SQL queries, table creation, and schema exploration.Last updated -3Python
- -securityFlicense-qualityA Model Context Protocol server that enables AI assistants to securely interact with Apache IoTDB databases through a controlled interface for listing tables, reading data, and executing SQL queries.Last updated -Python
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI assistants (Cursor, Windsurf, Claude Code) to interact with Microsoft SQL Server databases by providing connectivity through environment-configurable connections.Last updated -8302TypeScriptMIT License
- -securityAlicense-qualityA Model Context Protocol server that provides AI assistants with comprehensive access to SQL databases, enabling schema inspection, query execution, and database operations with enterprise-grade security.Last updated -42TypeScriptMIT License