mcp-duckdb-memory-server and mcp-database-server
The two tools are competitors within the "sql-database-mcp" category, as both provide a Model Context Protocol (MCP) server for querying SQL databases, with tool A specifically utilizing DuckDB for in-memory operations, and tool B offering broader support for SQLite, PostgreSQL, and MySQL.
About mcp-duckdb-memory-server
IzumiSy/mcp-duckdb-memory-server
MCP Memory Server with DuckDB backend
Implements a knowledge graph memory system storing entities, observations, and relations in DuckDB with SQL-backed queries, enabling scalable persistence beyond JSON file limitations. Combines DuckDB's analytical query engine with Fuse.js for fuzzy entity matching, supporting complex conditional searches and transaction integrity. Integrates with the Model Context Protocol (MCP) ecosystem for Claude Desktop and other MCP clients via stdio transport.
About mcp-database-server
ahmetbarut/mcp-database-server
A Model Context Protocol (MCP) server that provides multi-database query execution capabilities with support for SQLite, PostgreSQL, and MySQL databases. Includes a built-in Web UI for managing database connections.
Implements connection pooling with configurable limits and timeout settings, plus parameterized query execution with SQL injection protection via Zod validation. Persists all connection configs in a local SQLite store, enabling stateful management across server restarts, and integrates directly with Claude Desktop and Cursor IDE through stdio-based MCP transport.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work