Devrag

Name: Devrag
Author: tomohiro-owada

by tomohiro-owadacommunityv1.2.0

DevRag is a lightweight Retrieval-Augmented Generation (RAG) system designed for developers using Claude Code, enabling efficient document search and indexing to save tokens and time.

From the registry: Lightweight local RAG MCP server. 40x token reduction.

GitHub Repository

Install & configure

Prerequisites

required
Download devrag binary
Download the platform-specific binary from the DevRag releases page and place it in your PATH (e.g. /usr/local/bin).
https://github.com/tomohiro-owada/devrag/releases

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `devrag` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Download devrag binary** — Download the platform-specific binary from the DevRag releases page and place it in your PATH (e.g. /usr/local/bin). (https://github.com/tomohiro-owada/devrag/releases)

Canonical MCP server config (stdio transport):
- command: `/usr/local/bin/devrag`
- args: []
- optional environment variables:
  - `DEVRAG_THREADS`: CPU thread count (default 4) when running in CPU mode. (example: `4`)
  - `HTTP_PROXY`: HTTP proxy for downloading the embedding model on first run. (example: `<your-http-proxy>`)
  - `HTTPS_PROXY`: HTTPS proxy for downloading the embedding model on first run. (example: `<your-https-proxy>`)

Note: Local RAG over markdown files. Single Go binary; downloads an embedding model on first run.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Local RAG over markdown files. Single Go binary; downloads an embedding model on first run.