Step-by-step guides and how-to articles
View All Tags
Every REST API endpoint can become an MCP tool that AI agents discover and invoke automatically. The conversion is a mapping exercise: your OpenAPI spec already contains the tool name, description, parameters, and endpoint URL that MCP needs. This guide walks through the process from a single endpoint to bulk automation using ToolSet CRDs.
AI agents need a secure, standardized way to access your APIs. The Model Context Protocol (MCP) provides that bridge, and STOA Platform makes it trivial to deploy. In this tutorial, you'll learn how to set up a production-ready MCP gateway using Docker Compose in under 10 minutes.
New to MCP gateways? Start with our comprehensive guide: What is an MCP Gateway? to understand the architecture and security model before deploying.
By the end of this guide, you'll have a running gateway that exposes your existing REST APIs to AI agents like Claude, connects to authentication, and enforces runtime policies.
The Model Context Protocol (MCP) is a JSON-RPC 2.0 based protocol that standardizes how AI agents discover, authenticate with, and invoke external tools. It defines four phases — initialization, discovery, invocation, and streaming — over pluggable transports including SSE, WebSocket, and stdio. This article covers the protocol internals that matter for production deployments.