docs: add MCP (#419)

Author: mefellows

website/docs/docs/ai/index.md

@@ -5,6 +5,11 @@ sidebar_label: Introduction
 
 PactFlow's Test Generation feature, is an AI-powered capability designed to help users quickly generate Pact tests. By providing access to source code, OpenAPI descriptions, or traffic capture data, it reduces the time and effort needed to create and maintain contract tests.
 
+<div style={{textAlign: 'center'}}>
+  <img src="/img/mcp2.gif" width="1024" />
+  <p style={{marginTop: '-25px', fontStyle: 'italic', fontSize: '90%'}}>PactFlow AI with Copilot using MCP integration. Watch the <a href="https://www.youtube.com/watch?v=VNe_Y6FcBqA&t=444s">full video →</a></p>
+</div>
+
 ## Features
 
 PactFlow AI includes a suite of features to improve the efficiency and quality of your contract tests:
@@ -14,7 +19,7 @@ PactFlow AI includes a suite of features to improve the efficiency and quality o
 * Seamless integration with PactFlow's Role-based Access Controls feature, enabling you to enforce and manage organizational policies
 * Code review (beta), enabling you to evaluate the quality of existing Pact tests and suggest best-practice improvements
 
-PactFlow AI is available as a CLI and supports the following programming languages:
+PactFlow AI is available as a CLI or MCP server, and supports the following programming languages:
 
 * Java and Kotlin
 * TypeScript / JavaScript

website/docs/docs/ai/quick-start.md

@@ -17,6 +17,23 @@ You must be an Administrator or a user with the [`system_preference:manage:*` pe
 
 ## Installation
 
+### Option 1: MCP Server (Recommended)
+
+The Model Context Protocol (MCP) is the recommended way to use PactFlow AI. It provides seamless integration with IDEs and modern developer environments.
+
+MCP Server exposes PactFlow AI as a *local* endpoint and works with tools like VS Code, IntelliJ, Cursor, and other MCP-compatible agents.
+
+Follow the official [MCP Server documentation](https://developer.smartbear.com/smartbear-mcp/docs/mcp-server) to perform the following steps:
+
+* Install the MCP Server.
+* Configure and start the local service.
+* Connect with MCP clients.
+
+This option is ideal for teams working with AI copilots or looking to automate testing workflows.
+
+### Option 2: CLI
+
+You can also use PactFlow AI using the CLI. It supports test generation and review from the terminal.
 For *nix users (including Windows users running WSL/msys2/mingw), use the following command to download and install:
 
 ```sh
@@ -29,7 +46,7 @@ For Windows PowerShell users, use the following command to download and install:
 Invoke-WebRequest -Uri https://download.pactflow.io/ai/get.ps1 | Invoke-Expression
 ```
 
-### Installation Options
+#### Installation Options
 
 There are some options which you can set during installation.
 
@@ -48,7 +65,7 @@ curl https://download.pactflow.io/ai/get.sh | sh -s -- -h
 
 Verify the installation by running `pactflow-ai` to ensure it executes successfully.
 
-### Manual installation
+#### Manual installation
 
 Alternatively, download the latest version for your OS and architecture from the table below. Be sure to add it to your environment's `PATH`:
 
@@ -60,7 +77,7 @@ Linux GNU users will require glibc version 2.23 or later.
 Environments which do not use glibc, or use a version of glibc prior to 2.23, should instead use the musl variant.
 :::
 
-## Getting Started
+### Getting Started
 
 :::note
 Running `pactflow-ai --help` will show detailed usage for any subcommands.