Guide

Welcome to the Model Context Protocol (MCP) guide! This section will help you understand how to build and use MCP servers and clients.

What is MCP?

MCP (Model Context Protocol) is a protocol that enables Large Language Models (LLMs) like Claude to interact with external tools and data sources. With MCP, you can:

• Build servers that provide tools and data to LLMs
• Connect these servers to MCP-compatible clients
• Extend LLM capabilities with custom functionality

Core Concepts

MCP servers can provide three main types of capabilities:

1. Tools: Functions that can be called by the LLM (with user approval)
2. Resources: File-like data that can be read by clients (like API responses or file contents)
3. Prompts: Pre-written templates that help users accomplish specific tasks

Getting Started