Hal

Overview

Hal is a Model Context Protocol (MCP) server: HAL (HTTP API Layer) - An MCP server that provides HTTP API capabilities to Large Language Models. As an MCP server it plugs straight into AI assistants, exposing its functionality as tools the model can invoke on your behalf.

It runs locally: the npm package hal-mcp speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v1.0.14, published under the MIT license, with source at DeanWard/HAL on GitHub, where it has earned 38 stars.

You'll find Hal in the Development category here on mcp.site; it connects to Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and any other MCP client — see the install snippets below. If you maintain Hal for DeanWard, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "hal": {
      "command": "npx",
      "args": [
        "-y",
        "hal-mcp"
      ]
    }
  }
}