HAL (HTTP API Layer)
Make an HTTP GET request to a specified URL. Supports secret substitution using {secrets.key} syntax where 'key' corresponds to HAL_SECRET_KEY environment variables.
What is HAL (HTTP API Layer)?
HAL (HTTP API Layer) is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to make an http get request to a specified url. supports secret substitution using {secrets.key} syntax where 'key' corresponds to hal_secret_key environment variables.
Make an HTTP GET request to a specified URL. Supports secret substitution using {secrets.key} syntax where 'key' corresponds to HAL_SECRET_KEY environment variables.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- http-get
- http-post
- http-put
- http-patch
- http-delete
Use Cases
Maintainer
Works with
Installation
NPM
npx -y hal-mcpManual Installation
npx -y hal-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use HAL (HTTP API Layer)
HAL (HTTP API Layer) is a lightweight MCP server that gives AI assistants the ability to make arbitrary HTTP requests — GET, POST, PUT, PATCH, DELETE, OPTIONS, and HEAD — with secure secret injection so credentials are never exposed in prompts or tool arguments. It supports loading OpenAPI/Swagger specifications to auto-generate strongly typed tools from your API's operation IDs, and enforces URL allowlists and denylists to control which endpoints the AI can reach. Developers building AI integrations with REST APIs can use it as a universal HTTP client that keeps secrets safely in environment variables while letting the model construct and execute requests.
Prerequisites
- Node.js installed (npx available)
- Any API credentials stored as HAL_SECRET_* environment variables
- Optional: an OpenAPI/Swagger spec file or URL for auto-generated tools
- An MCP-compatible client such as Claude Desktop
Install and run HAL via npx
No permanent installation is needed. Run hal-mcp directly with npx, passing environment variables for your secrets and API configuration.
npx hal-mcpSet your secret environment variables
Store any API keys or tokens as HAL_SECRET_* variables. Use the {secrets.key} syntax in URLs and headers to reference them without exposing values to the model.
export HAL_SECRET_API_KEY=your_api_key_here
export HAL_SECRET_GITHUB_TOKEN=your_github_token
export HAL_API_BASE_URL=https://api.example.com
export HAL_SWAGGER_FILE=/path/to/openapi.jsonOptionally load an OpenAPI specification
Point HAL_SWAGGER_FILE at a local file or URL to an OpenAPI 3.x or Swagger 2.x spec. HAL will auto-generate one MCP tool per operation, named swagger_{operationId}.
export HAL_SWAGGER_FILE=https://petstore3.swagger.io/api/v3/openapi.jsonConfigure URL allowlists for security
Restrict which URLs the AI can call by setting HAL_WHITELIST_URLS, or block specific patterns with HAL_BLACKLIST_URLS.
export HAL_WHITELIST_URLS=https://api.example.com/*,https://api.github.com/*Add to your MCP client configuration
Configure Claude Desktop to launch hal-mcp via npx with your environment variables in the env block.
HAL (HTTP API Layer) Examples
Client configuration
Claude Desktop configuration for HAL. Secrets are passed as environment variables and referenced in requests using {secrets.key} syntax — values are never sent to the model.
{
"mcpServers": {
"hal": {
"command": "npx",
"args": ["hal-mcp"],
"env": {
"HAL_API_BASE_URL": "https://api.example.com",
"HAL_SECRET_API_KEY": "your_api_key_here",
"HAL_SECRET_GITHUB_TOKEN": "your_github_token",
"HAL_WHITELIST_URLS": "https://api.example.com/*,https://api.github.com/*"
}
}
}
}Prompts to try
Sample prompts demonstrating HAL's HTTP request tools and secret substitution capabilities.
- "Make a GET request to https://api.example.com/users with Authorization header Bearer {secrets.api_key} and show the results"
- "POST to https://api.github.com/repos/owner/repo/issues with my GitHub token and create an issue titled 'Bug report'"
- "List the available secrets so I know what credentials are configured in HAL"
- "Fetch the OpenAPI docs resource to see what auto-generated API tools are available"Troubleshooting HAL (HTTP API Layer)
Secret substitution not working — {secrets.key} appears literally in the request
Ensure the environment variable follows the exact naming convention: HAL_SECRET_ followed by the key name in UPPERCASE (e.g., HAL_SECRET_API_KEY maps to {secrets.api_key}). Dashes in the key name are converted to dots in namespace notation.
Request blocked with URL not allowed error
Check HAL_WHITELIST_URLS includes the target domain with a wildcard pattern (e.g., https://api.example.com/*). If HAL_BLACKLIST_URLS is set, confirm the URL is not matched by a blacklist pattern which takes precedence.
OpenAPI-generated tools do not appear in the client
Verify HAL_SWAGGER_FILE points to a valid and reachable OpenAPI 3.x or Swagger 2.x specification. Run npx hal-mcp with LOG_LEVEL=debug to see spec loading errors. Each operation must have a unique operationId for tool generation to succeed.
Frequently Asked Questions about HAL (HTTP API Layer)
What is HAL (HTTP API Layer)?
HAL (HTTP API Layer) is a Model Context Protocol (MCP) server that make an http get request to a specified url. supports secret substitution using {secrets.key} syntax where 'key' corresponds to hal_secret_key environment variables. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install HAL (HTTP API Layer)?
Install via npm with the command: npx -y hal-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with HAL (HTTP API Layer)?
HAL (HTTP API Layer) works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is HAL (HTTP API Layer) free to use?
Yes, HAL (HTTP API Layer) is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
HAL (HTTP API Layer) Alternatives — Similar Developer Tools Servers
Looking for alternatives to HAL (HTTP API Layer)? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up HAL (HTTP API Layer) in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use HAL (HTTP API Layer)?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.