RAG-DuckDB
This MCP server provides AI assistants with document processing and retrieval-augmented generation capabilities using DuckDB as the vector database backend, built by niksh06 using Python with FastAPI and sentence-transformers for multilingual embeddings. The implementation features intelligent chunking strategies that adapt to file types (AST parsing for code, specialized splitters for markdown and configuration files), supports over 20 file formats including programming languages and documentation formats, and offers hybrid search combining semantic similarity with BM25 keyword search plus optional cross-encoder reranking. Built with Docker containerization, CPU/GPU flexibility, TF-IDF keyword extraction for enhanced search, and a web interface alongside JSON API endpoints, it serves developers needing local document indexing without external dependencies, teams requiring code-aware chunking for technical documentation, and organizations wanting self-hosted RAG capabilities with advanced search features and multi-format document support.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · 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/niksh06/rag-duckdb-with-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve RAG-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.