Ask Llm

Overview

Ask Llm is a Model Context Protocol (MCP) server: Unified MCP server — auto-detects Gemini, Codex, Claude, Ollama, and Antigravity providers. In practice that means any MCP-compatible AI assistant can call Ask Llm's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the npm package @ask-llm/mcp speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.6.2, published under the MIT license, with source at Lykhoyda/ask-llm on GitHub, where it has earned 16 stars.

Ask Llm is listed under Development 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 Ask Llm for Lykhoyda, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "ask_llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ]
    }
  }
}