Privacy-first document search server running entirely locally. Supports semantic search over PDFs, DOCX, TXT, and Markdown files with LanceDB vector storage and local embeddings - no API keys or cloud services required.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y mcp-local-ragAgent-CoreX intelligently routes which tools from shinpr/mcp-local-rag your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"mcp-local-rag": {
"command": "npx",
"args": [
"-y",
"mcp-local-rag"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add mcp-local-ragAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use shinpr/mcp-local-rag directly without routing
npx -y mcp-local-ragNew to Agent-CoreX? View setup guide →