# io.github.tomohiro-owada/devrag

> Use this tool when you need to efficiently manage and reduce token sizes for local RAG (Retrieval-Augmented Generation) model serving, providing a lightweight MCP (Model Control Plane) server solution that achieves 40x token reduction. It solves problems related to token size and model serving efficiency, making it ideal for applications with limited resources. The tool takes in RAG models and outputs optimized token sizes, streamlining the development process.

Canonical page: https://skillsregistry.net/skills/io-github-tomohiro-owada-devrag  
JSON: https://api.skillsregistry.net/v1/skills/io-github-tomohiro-owada-devrag

## Description

Lightweight local RAG MCP server. 40x token reduction.

## Trust

- **Trust score (0–1):** 0.80
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.2.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.tomohiro-owada%2Fdevrag)
- **Repository:** <https://github.com/tomohiro-owada/devrag>

## 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": "io-github-tomohiro-owada-devrag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-tomohiro-owada-devrag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-tomohiro-owada-devrag/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