Jampp MCP Server logo

Jampp MCP Server

by springwq

This MCP server provides access to the Jampp Reporting API through the Model Context Protocol. It allows LLMs to fetch campaign performance data.

View on GitHub

Last updated: N/A

What is Jampp MCP Server?

The Jampp MCP Server is a tool that allows Large Language Models (LLMs) to access and retrieve campaign performance data from the Jampp Reporting API using the Model Context Protocol. It acts as a bridge between the LLM and the Jampp API.

How to use Jampp MCP Server?

To use the server, you need to clone the repository, install the dependencies, set up your Jampp API credentials in a .env file, and run the server. You can then integrate it with tools like MCP Inspector or Claude Desktop by configuring them to use the server's endpoint. Once integrated, you can use natural language queries within Claude to fetch campaign data.

Key features of Jampp MCP Server

  • OAuth 2.0 authentication with automatic token refresh

  • GraphQL-based API integration

  • Campaign spend reporting

  • Comprehensive performance metrics

Use cases of Jampp MCP Server

  • Fetching campaign spend for a specific date range

  • Tracking daily spend for a campaign

  • Retrieving performance metrics for campaigns

  • Generating asynchronous reports for large datasets

FAQ from Jampp MCP Server

What is the Model Context Protocol (MCP)?

MCP is a protocol that allows LLMs to interact with external data sources and tools.

What are the prerequisites for running the server?

You need Python 3.10 or higher and Jampp API credentials (Client ID and Client Secret).

How do I install the dependencies?

You can use uv add "mcp[cli]" httpx python-dotenv or pip install "mcp[cli]" httpx python-dotenv.

How do I configure Claude Desktop to use this server?

You need to modify the claude_desktop_config.json file to include the server's command and environment variables.

What kind of queries can I ask Claude after integrating this server?

You can ask questions like "Show me the campaign spend for the last 30 days" or "What was the daily spend for campaign ID 12345 last week?"