Skip to main content
MCP Server

HAPI MCP server: Dynamically exposes OpenAPI REST APIs as MCP tools for AI assistants

Share
0 stars TypeScript Unknown Updated: 2026-01-07

Send to Your Agent

Copy this prompt and paste it into Claude, Cursor, or any MCP client to install instantly.

Install the HAPI MCP Server MCP server for me.

Server: HAPI MCP Server
Description: HAPI MCP server: Dynamically exposes OpenAPI REST APIs as MCP tools for AI assistants
Install command: 

Environment variables needed:
- HAPI_FQDN: Fully Qualified Domain Name for the HAPI server (used in MCP tool URLs)
- HAPI_HOME: Directory path for HAPI configuration and specs. Should be mounted as a volume in Docker
- PROJECT_NAME: The name of the project/API (alternative to positional argument)
- HAPI_OPENAPI: OpenAPI spec URL or path (alternative to --openapi flag)
- HAPI_URL: Backend API base URL (alternative to --url flag)
- HAPI_PORT: Server port (alternative to --port flag) - this is the internal container port
- HAPI_HEADLESS: Enable headless mode (alternative to --headless flag)
- HAPI_MCP: Enable MCP mode (alternative to --mcp flag)
- HAPI_DEV: Enable development mode (alternative to --dev flag)
- HAPI_CORS: Comma-separated allowed CORS origins (alternative to --cors flag)
- HAPI_CONFIG_FILES: Comma-separated configuration files (alternative to --filename flag)
- NODE_ENV: Node environment (development, production). 'development' enables verbose logging and debugging features.

GitHub: https://github.com/larebelion/hapimcp

Please install this MCP server and confirm when ready.

Paste into any AI agent with MCP support — works with Claude Desktop, Cursor, Cline, and more.

Quick Install

Config file: ~/Library/Application Support/Claude/claude_desktop_config.json

  1. Open Claude Desktop app
  2. Go to Settings → Developer → Edit Config
  3. Paste the config below into the file
  4. Restart Claude Desktop

Add this to your ~/Library/Application Support/Claude/claude_desktop_config.json

Installation Methods

Tools (1)

execute

Execute HAPI MCP Server operations

Environment Variables

HAPI_FQDN Optional

Fully Qualified Domain Name for the HAPI server (used in MCP tool URLs)

Example: localhost
HAPI_HOME Optional

Directory path for HAPI configuration and specs. Should be mounted as a volume in Docker

Example: /app/.hapi
PROJECT_NAME Optional

The name of the project/API (alternative to positional argument)

Example: value
HAPI_OPENAPI Optional

OpenAPI spec URL or path (alternative to --openapi flag)

Example: value
HAPI_URL Optional

Backend API base URL (alternative to --url flag)

Example: value
HAPI_PORT Optional

Server port (alternative to --port flag) - this is the internal container port

Example: 3030
HAPI_HEADLESS Optional

Enable headless mode (alternative to --headless flag)

Example: true
HAPI_MCP Optional

Enable MCP mode (alternative to --mcp flag)

Example: true
HAPI_DEV Optional

Enable development mode (alternative to --dev flag)

Example: value
HAPI_CORS Optional

Comma-separated allowed CORS origins (alternative to --cors flag)

Example: value
HAPI_CONFIG_FILES Optional

Comma-separated configuration files (alternative to --filename flag)

Example: value
NODE_ENV Optional

Node environment (development, production). 'development' enables verbose logging and debugging features.

Example: production

Compatibility

Claude Desktop
Cursor
Cline
VS Code
Devin (formerly Windsurf)

About

HAPI MCP server: Dynamically exposes OpenAPI REST APIs as MCP tools for AI assistants

Overview

HAPI MCP server: Dynamically exposes OpenAPI REST APIs as MCP tools for AI assistants

Repository

Find the source code at https://github.com/larebelion/hapimcp.

Tools

  • execute: Execute HAPI MCP Server operations

Environment Variables

  • HAPI_FQDN: Fully Qualified Domain Name for the HAPI server (used in MCP tool URLs)
  • HAPI_HOME: Directory path for HAPI configuration and specs. Should be mounted as a volume in Docker
  • PROJECT_NAME: The name of the project/API (alternative to positional argument)
  • HAPI_OPENAPI: OpenAPI spec URL or path (alternative to --openapi flag)
  • HAPI_URL: Backend API base URL (alternative to --url flag)
  • HAPI_PORT: Server port (alternative to --port flag) - this is the internal container port
  • HAPI_HEADLESS: Enable headless mode (alternative to --headless flag)
  • HAPI_MCP: Enable MCP mode (alternative to --mcp flag)
  • HAPI_DEV: Enable development mode (alternative to --dev flag)
  • HAPI_CORS: Comma-separated allowed CORS origins (alternative to --cors flag)
  • HAPI_CONFIG_FILES: Comma-separated configuration files (alternative to --filename flag)
  • NODE_ENV: Node environment (development, production). 'development' enables verbose logging and debugging features.

Related Resources

HAPI Strava MCP Server

MCP Server

Strava MCP tools for AI: athletes, activities, segments, clubs, routes. Powered by HAPI MCP server.

MCP Server Builder

Skill

Build high-quality Model Context Protocol (MCP) servers to integrate external APIs and services with AI assistants. Follow best practices for tool design, security, and cross-platform compatibility.

MCP Tool Orchestrator

Prompt

Design and orchestrate complex multi-tool workflows using the Model Context Protocol (MCP). Build intelligent agent systems that coordinate multiple MCP servers for sophisticated automation tasks.

MCP

Glossary

MCP stands for Model Context Protocol. It is an open standard that lets AI clients connect to external tools, data sources, and prompts through a single, consistent interface. Anthropic introduced MCP in late 2024, and it has since been adopted by Claude Desktop, Cursor, Cline, VS Code, Windsurf, and a growing list of community clients. An MCP server is a small program that exposes three things: tools the model can call, resources the client can read, and prompts that help users accomplish common tasks. An MCP client discovers those capabilities and decides when to invoke them. Transport is usually stdio for local servers or Server-Sent Events for remote ones. For developers, MCP removes the need to build a custom integration for every API. You write one server, and any compatible client can use it. For users, it means AI assistants can securely access files, databases, SaaS tools, and web services without each client reinventing the wheel.

MCP Registry Server

MCP Server

Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.

Compare LLM Pricing

This server works with Claude, GPT-4o, and other models. Compare API costs side-by-side to find the cheapest option for your workflow.