Jampp MCP Server

🚀 Jampp MCP Server

This MCP server provides access to the Jampp Reporting API through the Model Context Protocol, allowing Large Language Models (LLMs) to retrieve campaign performance data.

🚀 Quick Start

The Jampp MCP Server offers seamless access to the Jampp Reporting API, enabling LLMs to obtain campaign performance data. Here's how to get started:

✨ Features

• OAuth 2.0 authentication with automatic token refresh
• GraphQL-based API integration
• Campaign spend reporting
• Daily spend tracking
• Comprehensive performance metrics
• Asynchronous report generation and retrieval
• Inventory of available metrics and dimensions

📦 Installation

Prerequisites

• Python 3.10 or higher
• Jampp API credentials (Client ID and Client Secret)

Steps

1. Clone this repository:

   git clone https://github.com/yourusername/mcp-jampp.git
   cd mcp-jampp
   

2. Install the dependencies:

   uv add "mcp[cli]" httpx python-dotenv
   

   Or use pip:

   pip install "mcp[cli]" httpx python-dotenv
   

3. Set up environment variables: Create a .env file in the project root directory with your Jampp API credentials:

   JAMPP_CLIENT_ID=your_client_id
   JAMPP_CLIENT_SECRET=your_client_secret
   

💻 Usage Examples

Run the server directly

python jampp_mcp_server.py

Use with MCP Inspector (for development and testing)

mcp dev jampp_mcp_server.py

Integrate with Claude Desktop

1. Download and install Claude Desktop from claude.ai/download.

2. Configure Claude Desktop to use this server:

   • Open or create ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).
   • Add the following configuration:

   {
     "mcpServers": {
       "jampp": {
         "command": "python",
         "args": ["path/to/jampp_mcp_server.py"],
         "env": {
           "JAMPP_CLIENT_ID": "your_client_id",
           "JAMPP_CLIENT_SECRET": "your_client_secret"
         }
       }
     }
   }
   

3. Restart Claude Desktop.

Available Tools

1. get_campaign_spend

Retrieve campaign spend data for a specific date range.

Parameters:

• from_date: Start date in YYYY-MM-DD format
• to_date: End date in YYYY-MM-DD format
• campaign_id (optional): Campaign ID

2. get_campaign_performance

Retrieve campaign performance data.

Parameters:

• from_date: Start date in YYYY-MM-DD format
• to_date: End date in YYYY-MM-DD format
• campaign_id (optional): Campaign ID

3. generate_report

Generate a custom report.

Parameters:

• report_type: Report type (e.g., 'daily', 'weekly', 'monthly')
• from_date: Start date in YYYY-MM-DD format
• to_date: End date in YYYY-MM-DD format

Example Queries

# Get campaign spend
python -m mcp_server get_campaign_spend --from_date 2023-01-01 --to_date 2023-12-31

# Get campaign performance
python -m mcp_server get_campaign_performance --campaign_id 12345 --from_date 2023-01-01 --to_date 2023-12-31

# Generate a monthly report
python -m mcp_server generate_report --report_type monthly --from_date 2023-01-01 --to_date 2023-12-31

📄 License

This project is licensed under the MIT License.