The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you’re building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

​
Get started with MCP

Choose the path that best fits your needs:

Quickstart

The fastest way to see MCP in action—connect example servers to Claude Desktop

Build your first server (Python)

Create a simple MCP server in Python to understand the basics

Build your first server (TypeScript)

Create a simple MCP server in TypeScript to understand the basics

​
Development tools

Essential tools for building and debugging MCP servers:

Debugging Guide

Learn how to effectively debug MCP servers and integrations

MCP Inspector

Test and inspect your MCP servers with our interactive debugging tool

​
Explore MCP

Dive deeper into MCP’s core concepts and capabilities:

Core Architecture

Understand how MCP connects clients, servers, and LLMs

Resources

Expose data and content from your servers to LLMs

Prompts

Create reusable prompt templates and workflows

Tools

Enable LLMs to perform actions through your server

Sampling

Let your servers request completions from LLMs

Transports

Learn about MCP’s communication mechanism

​
Contributing

Want to contribute? Check out @modelcontextprotocol on GitHub to join our growing community of developers building with MCP.

Was this page helpful?

Quickstart