Hal

Name: Hal
Author: DeanWard

by DeanWardcommunityv1.0.14

HAL is a Model Context Protocol (MCP) server that provides HTTP API capabilities to Large Language Models, enabling them to make HTTP requests and interact with web APIs through a secure interface.

From the registry: HAL (HTTP API Layer) - An MCP server that provides HTTP API capabilities to Large Language Models

GitHub Repository

Install & configure

Prerequisites

required
Node.js 18+
Node.js runtime
https://nodejs.org

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `hal` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Node.js 18+** — Node.js runtime (https://nodejs.org)

Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["hal-mcp"]
- optional environment variables:
  - `HAL_SWAGGER_FILE`: Path or URL to OpenAPI/Swagger specification file (example: `/path/to/openapi.json`)
  - `HAL_API_BASE_URL`: Base URL for API requests (overrides servers in spec) (example: `<your-api-base-url>`)
  - `HAL_WHITELIST_URLS`: Comma-separated URL patterns to allow (example: `https://api.github.com/*`)
  - `HAL_BLACKLIST_URLS`: Comma-separated URL patterns to block (example: `http://localhost:*`)

Note: Also supports HAL_SECRET_* env vars for secure secret substitution using {secrets.key} templates, and HAL_ALLOW_* for namespaced URL restrictions.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Also supports HAL_SECRET_* env vars for secure secret substitution using {secrets.key} templates, and HAL_ALLOW_* for namespaced URL restrictions.