# claude-rag

> claude-rag — sangelastro-claude-rag. Use this tool when you need to efficiently search and retrieve information from Markdown files using semantic search capabilities. It solves problems related to knowledge discovery and information retrieval by indexing files into a local SQLite vector store. The claude-rag tool takes Markdown files as input and provides relevant search results as output, ideal for use cases where intuitive and accurate search functionality is required.

Canonical page: https://skillsregistry.net/skills/sangelastro-claude-rag  
JSON: https://api.skillsregistry.net/v1/skills/sangelastro-claude-rag

## Description

MCP server that indexes Markdown files into a local SQLite vector store and provides semantic search tools for Claude Code.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/byogrf9m22)
- **Repository:** <https://github.com/sangelastro/claude-rag>

## 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": "sangelastro-claude-rag"
    }
  }
}
```

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