Welcome, Challenger!
This is the first phase of your journey. Your goal is to understand the Model Context Protocol (MCP) and find the hidden endpoint on this server.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open standard that functions as the universal connector—often described as the "USB-C for AI applications"—bridging the gap between Large Language Models (LLMs) and external data or tools.
Traditionally, AI models were isolated "brains in a jar," limited to their training data. MCP breaks this isolation by standardizing how AI clients (like Claude or IDEs) discover and communicate with servers (like local databases or cloud APIs) to fetch resources or execute commands.
This is a game-changer for Agentic AI. Instead of building custom integrations for every tool, MCP provides a scalable ecosystem where a tool built once works across any compliant application. However, this power introduces new attack surfaces—from prompt injection to unauthorized execution—which is exactly why you are here.
Find the Hidden Endpoint
Your mission, should you choose to accept it, is to find the MCP endpoint on this server. Here are a few hints to get you started:
- MCP endpoints are often named after the protocol itself.
- The endpoint is part of the same web application you are currently viewing.
- You might need to use your browser's developer tools to get more information.
Once you find the endpoint, you will need to interact with it to get the flag for this phase. Good luck!
Phase 1 Flag
Once you have found the flag, enter it below to check your answer.