Hal

Hal is an open-source Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to securely interact with any HTTP API. It exposes tool interfaces for HTTP requests (GET/POST/PUT/PATCH/DELETE/OPTIONS/HEAD), supports secure secret management with automatic redaction, and can auto-generate tools from Swagger/OpenAPI specifications for seamless API integration. Hal is suitable for advanced users, developers, and organizations wanting to enhance AI assistants (like Claude, Cursor, Windsurf, or any MCP-compatible client) with real-time HTTP API integration and secure access to web resources.