SQL Database Assistant
Multi-database MCP server implementation by Sharan Sahu that provides AI assistants with intelligent SQL querying capabilities across SQLite, MySQL, and Oracle databases through a web-based chat interface. The implementation features database-specific MCP servers with comprehensive schema introspection tools, intelligent text matching with Unicode normalization and wildcard escaping, and a Flask-powered web frontend that connects OpenAI's GPT models with database tools via the Model Context Protocol. Built with extensive SQL dialect awareness including Oracle's case-sensitive identifiers, MySQL's collation handling, and SQLite's limited regex support, plus defensive data normalization for common field types like booleans, prices, and durations, it serves developers needing conversational database access, data analysts requiring natural language SQL generation, and teams building AI-powered database query interfaces where proper text matching and cross-database compatibility are essential.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/sharansahu/mcp-sql
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve SQL Database Assistant from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.