MCP Directory

tomohiro-owada/devrag

GitHub
Productivity

Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x with sqlite-vec and multilingual-e5-small embeddings. Supports filtered search by directory and filename patterns.

Direct install

Run the underlying MCP server directly — without Agent-CoreX routing.

npx -y devrag

Use with Agent-CoreX

Agent-CoreX intelligently routes which tools from tomohiro-owada/devrag your AI agent actually needs per request — reducing token usage and cost.

agent-corex.json

{
  "mcpServers": {
    "devrag": {
      "command": "npx",
      "args": [
        "-y",
        "devrag"
      ]
    }
  }
}

Route tomohiro-owada/devrag intelligently

Connect in 2 minutes. Only pay for the tools your agent actually uses.

Installation Guide

Use with Agent-CoreX

Recommended: intelligent tool routing, lower costs

uvx agent-corex mcp add devrag

Agent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.

Direct Install

Use tomohiro-owada/devrag directly without routing

npx -y devrag

New to Agent-CoreX? View setup guide →

tomohiro-owada/devrag MCP Server — Agent-CoreX