a

src/AI/AI-MCP-Servers.md

@@ -2,11 +2,10 @@
 
 {{#include ../banners/hacktricks-training.md}}
 
-- (https://modelcontextprotocol.io/introduction
 
 ## What is MPC - Model Context Protocol
 
-The **Model Context Protocol (MCP)** is an open standard that allows AI models (LLMs) to connect with external tools and data sources in a plug-and-play fashion. This enables complex workflows: for example, an IDE or chatbot can *dynamically call functions* on MCP servers as if the model naturally "knew" how to use them. Under the hood, MCP uses a client-server architecture with JSON-based requests over various transports (HTTP, WebSockets, stdio, etc.).
+The [**Model Context Protocol (MCP)**](https://modelcontextprotocol.io/introduction) is an open standard that allows AI models (LLMs) to connect with external tools and data sources in a plug-and-play fashion. This enables complex workflows: for example, an IDE or chatbot can *dynamically call functions* on MCP servers as if the model naturally "knew" how to use them. Under the hood, MCP uses a client-server architecture with JSON-based requests over various transports (HTTP, WebSockets, stdio, etc.).
 
 A **host application** (e.g. Claude Desktop, Cursor IDE) runs an MCP client that connects to one or more **MCP servers**. Each server exposes a set of *tools* (functions, resources, or actions) described in a standardized schema. When the host connects, it asks the server for its available tools via a `tools/list` request; the returned tool descriptions are then inserted into the model's context so the AI knows what functions exist and how to call them.
 

src/AI/AI-Unsupervised-Learning-algorithms.md

@@ -2,8 +2,8 @@
 
 {{#include ../banners/hacktricks-training.md}}
 
-## Unsupervised Learning
 
+## Unsupervised Learning
 
 Unsupervised learning is a type of machine learning where the model is trained on data without labeled responses. The goal is to find patterns, structures, or relationships within the data. Unlike supervised learning, where the model learns from labeled examples, unsupervised learning algorithms work with unlabeled data.
 Unsupervised learning is often used for tasks such as clustering, dimensionality reduction, and anomaly detection. It can help discover hidden patterns in data, group similar items together, or reduce the complexity of the data while preserving its essential features.

src/AI/README.md

@@ -7,19 +7,19 @@
 The best starting point to learn about AI is to understand how the main machine learning algorithms work. This will help you to understand how AI works, how to use it and how to attack it:
 
 {{#ref}}
-AI-Supervised-Learning-Algorithms.md
+./AI-Supervised-Learning-Algorithms.md
 {{#endref}}
 
 {{#ref}}
-AI-Unsupervised-Learning-Algorithms.md
+./AI-Unsupervised-Learning-Algorithms.md
 {{#endref}}
 
 {{#ref}}
-AI-Reinforcement-Learning-Algorithms.md
+./AI-Reinforcement-Learning-Algorithms.md
 {{#endref}}
 
 {{#ref}}
-AI-Deep-Learning.md
+./AI-Deep-Learning.md
 {{#endref}}
 
 ### LLMs Architecture