Velocirag

Overview

Velocirag is a Model Context Protocol (MCP) server: Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search. In practice that means any MCP-compatible AI assistant can call Velocirag's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package velocirag (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.7.4, published under the MIT license, with source at HaseebKhalid1507/VelociRAG on GitHub, where it has earned 11 stars.

Velocirag is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Velocirag for HaseebKhalid1507, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "velocirag": {
      "command": "uvx",
      "args": [
        "velocirag"
      ]
    }
  }
}