MCP is not a framework and does not compete with the others here. It is a protocol. Instead of writing a bespoke integration for every agent and every data source, a tool is exposed once as an MCP server and any MCP aware agent can use it.
Reach for it when
- You want your tools reusable across agents and frameworks
- You are connecting agents to databases, files or internal APIs
- You want to publish an integration once rather than per framework
Look elsewhere when
- You have two tools and one agent. Plain function calling is simpler
What the lessons will cover
- 01What MCP solves
- 02Servers, clients and transports
- 03Your first MCP server
- 04Tools
- 05Resources
- 06Prompts
- 07Connecting a client
- 08Shipping a server
Others in protocol and tools
Common questions
Is MCP free to use?
MCP is open source and free to run yourself. You still pay whichever model provider you point it at, and this tutorial is free with no signup.
Do I need to know Python to use MCP?
Basic Python is enough. Functions, dictionaries and imports cover most of what MCP asks of you.
When should I not use MCP?
You have two tools and one agent. Plain function calling is simpler.
Lessons for MCP are being written. Meanwhile the LangGraph tutorial covers the same ground: state, tools, loops, memory and human approval. Most of it carries straight over.
Start the LangGraph tutorial →