MCP Campaign Server

A Spring Boot MCP (Model Context Protocol) server that provides insurance marketing campaign management capabilities for Claude AI integration.

Features

• Audience Targeting: AI-powered recommendations for insurance marketing audience segmentation
• Campaign Content: Personalized content recommendations for different insurance products and channels
• Claude Inspector Integration: Support for Claude Inspector tool queries
• MCP Protocol: Full MCP server implementation with WebSocket support
• REST API: Additional HTTP endpoints for direct integration

Quick Start

Prerequisites

• Java 17 or higher
• Maven 3.6 or higher

Installation

1. Clone the repository:

git clone <repository-url>
cd Mcp_Campaign

2. Build the project:

# If you have corporate Maven repository issues, use the startup script
./start.sh

# Or manually with custom settings
mvn clean compile --settings temp-settings.xml

3. Run the application:

mvn spring-boot:run

The server will start on port 8080 with WebSocket endpoint at ws://localhost:8080/api/mcp

Corporate Repository Issues

If you encounter corporate Maven repository connectivity issues, create a temporary settings file:

# Create temp-settings.xml with Maven Central only
cat > temp-settings.xml << EOF
<?xml version="1.0" encoding="UTF-8"?>
<settings xmlns="http://maven.apache.org/SETTINGS/1.0.0"
          xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
          xsi:schemaLocation="http://maven.apache.org/SETTINGS/1.0.0 
          http://maven.apache.org/xsd/settings-1.0.0.xsd">
    <mirrors>
        <mirror>
            <id>central</id>
            <name>Maven Central</name>
            <url>https://repo1.maven.org/maven2</url>
            <mirrorOf>*</mirrorOf>
        </mirror>
    </mirrors>
</settings>
EOF

# Then build with custom settings
mvn clean compile --settings temp-settings.xml

MCP Tools

The server provides the following MCP tools for Claude integration:

1. audience_targeting

Provides audience targeting criteria recommendations based on user requirements.

Input Parameters:

• requirements (required): User requirements for audience targeting
• insurance_type (optional): Type of insurance (life, health, auto, property, etc.)
• campaign_objective (optional): Campaign objective (acquisition, retention, upselling, etc.)

Example Usage:

{
  "name": "audience_targeting",
  "arguments": {
    "requirements": "Target young professionals aged 25-35 who are interested in life insurance",
    "insurance_type": "life_insurance",
    "campaign_objective": "acquisition"
  }
}

2. campaign_content_recommendation

Recommends personalized campaign content for insurance marketing.

Input Parameters:

• audience_criteria (required): Target audience criteria object
• insurance_type (required): Type of insurance product
• channel (optional): Marketing channel (email, sms, social_media, etc.)
• campaign_goal (optional): Campaign goal (awareness, conversion, retention, etc.)

Example Usage:

{
  "name": "campaign_content_recommendation",
  "arguments": {
    "audience_criteria": {
      "minAge": 25,
      "maxAge": 35,
      "incomeRange": ["middle_income", "high_income"]
    },
    "insurance_type": "life_insurance",
    "channel": "email",
    "campaign_goal": "conversion"
  }
}

3. inspector_query

Executes queries for Claude Inspector tool integration.

Input Parameters:

• query (required): Query for Claude Inspector tool

Example Usage:

{
  "name": "inspector_query",
  "arguments": {
    "query": "Analyze the effectiveness of recent insurance marketing campaigns"
  }
}

REST API Endpoints

Health Check

GET /api/campaigns/health

List Available Tools

GET /api/campaigns/tools

Audience Recommendation

POST /api/campaigns/audience/recommend
Content-Type: application/

... [View full README on GitHub](https://github.com/AlandeXiong/mcp_campaign_server#readme)