# RAG-DuckDB

> Use this tool when you need to process and retrieve documents, or generate text based on existing information, and require advanced search features and support for multiple file formats. It solves problems such as document indexing, code-aware chunking, and semantic search, and accepts various file types as input, outputting relevant information and generated text through a web interface or JSON API endpoints. Ideal for use cases where local document indexing and self-hosted retrieval-augmented generation are necessary, such as developer teams and organizations with technical documentation needs.

Canonical page: https://skillsregistry.net/skills/niksh06-rag-duckdb  
JSON: https://api.skillsregistry.net/v1/skills/niksh06-rag-duckdb

## Description

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.

## Trust

- **Trust score (0–1):** 0.37
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/niksh06-rag-duckdb)
- **Repository:** <https://github.com/niksh06/rag-duckdb-with-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "niksh06-rag-duckdb"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/niksh06-rag-duckdb` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/niksh06-rag-duckdb/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt