DuckDB
MCPlucker is a Go-based MCP server that provides direct access to DuckDB's analytical capabilities through five core tools: file-to-table loading (CSV, JSON, Parquet), table management, schema inspection, and SQL query execution with configurable result limits. Built with the go-duckdb driver and MCP Go SDK, it uses an in-memory DuckDB instance by default and includes comprehensive error handling, automatic file type detection, and structured JSON responses for all operations. The implementation follows a clean architecture with separate packages for database management, server logic, and tool implementations, making it ideal for data analysts and developers who need fast, local analytical processing of structured data files without the overhead of a full database setup.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/dacort/mcplucker
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve DuckDB 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.