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.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y devragAgent-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"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add devragAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use tomohiro-owada/devrag directly without routing
npx -y devragNew to Agent-CoreX? View setup guide →