The problem MCP solves
Before MCP, every AI agent had its own way of connecting to external tools. MCP proposes a universal protocol: an MCP server exposes tools and resources in a standard format any MCP client can use.
Key concepts
Tools
An MCP tool is a function the agent can call: search a file, run a SQL query, send an email. Each tool has a name, a natural language description and a JSON schema for parameters.
Resources
Resources are data the agent can read passively: file contents, a web page, a database record.
Simple analogy: think of MCP as a universal USB-C connector. Your AI agent is the computer. MCP servers are the devices. The protocol is the USB-C standard.
Build your first MCP server in Python
Install the SDK: pip install mcp. Create your server with @server.tool() to define your tools. Add your server to Claude Desktop or Cursor config. Your tools are immediately available.
Essential MCP servers
MCP Filesystem, MCP PostgreSQL, MCP Slack, MCP GitHub, MCP Brave Search. All open source, all free.
MCP, exposing tools to agents and securing them are covered hands-on in the AI Engineering Bootcamp.
