All Topics
Model Context Protocol
MCP
MCP is Anthropic's open protocol that lets AI models connect securely to tools, APIs, and data sources through a standardised interface. Think of it as USB-C for AI. One universal connector for everything your model needs to interact with the outside world.
Lessons
1
What is MCP and Why Does It Matter?
The problem of fragmented AI tool integrations and how MCP fixes them with a single protocol.
2
MCP Architecture: Hosts, Clients, Servers
Understand the three-layer architecture and how messages flow between each component.
3
Tools, Resources, and Prompts
The three primitives MCP exposes and how a model uses each one to interact with external systems.
4
Transport Layers: stdio vs SSE
Local vs remote MCP servers and when to choose each transport option.
5
Security Model and Permissions
How MCP handles authentication, authorisation, and sandboxing tool execution safely.
6
Build Your First MCP Server
Step by step: create a working MCP server in Python that exposes a real, callable tool.