Model Context Protocol (MCP)
MCP is the open standard for connecting AI to data sources and tools. Think of it as USB-C for AI.
Instead of writing custom API wrappers for every service, you run an MCP Server. The MCP Server exposes standard Tools, Resources (read-only data), and Prompts.
- MCP Servers: Lightweight connectors to databases, Jira, GitHub, local files, etc.
- MCP Clients: Applications like Claude Desktop, Cursor, or your custom agent framework that consume the server.
- Transports: Connect via local
stdio or remote SSE (Server-Sent Events).
💡 Key Insight: MCP separates the "thinking" (the LLM) from the "doing" (the tools). Because it is a unified protocol, you can hot-swap any compatible agent client with any compatible tool server.