Active Development

The AutoMCP CLI and SDK are currently in active development. Features and APIs may change. Please check our GitHub repository for the latest updates and documentation.

Documentation

Installation

Install the AutoMCP Python CLI using pip:

$ pip install amcp

Quick Start

Deploy your first MCP server in 3 simple steps:

1. Create your API specification

Create an OpenAPI specification file (or use an existing one):

{
  "openapi": "3.0.0",
  "info": {
    "title": "My API",
    "version": "1.0.0"
  },
  "paths": {
    "/hello": {
      "get": {
        "summary": "Say hello",
        "responses": {
          "200": {
            "description": "Success"
          }
        }
      }
    }
  }
}

2. Deploy with AutoMCP

Run the deploy command:

$ amcp deploy ./my-api.json --name my-service

3. Connect with MCP clients

Your server is now live and ready to use with any MCP client.

Configuration

Configure your MCP server with command-line options:

Available Options

--name
Name for your MCP server (required)
--auth
Authentication type: none, api-key, jwt, oauth2
--rate-limit
Rate limiting (e.g., 1000/hour)
--region
Deployment region (default: auto)

Need more help?

Join our community or check out more resources:

GitHubBlogEmail Support