MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

​
Why MCP?

Image for: ​Why MCP?

MCP helps you build agents and complex workflows on top of LLMs. LLMs frequently need to integrate with data and tools, and MCP provides:

  • A growing list of pre-built integrations that your LLM can directly plug into
  • The flexibility to switch between LLM providers and vendors
  • Best practices for securing your data within your infrastructure

​
General architecture

At its core, MCP follows a client-server architecture where a host application can connect to multiple servers:

  • MCP Hosts: Programs like Claude Desktop, IDEs, or AI tools that want to access data through MCP
  • MCP Clients: Protocol clients that maintain 1:1 connections with servers
  • MCP Servers: Lightweight programs that each expose specific capabilities through the standardized Model Context Protocol
  • Local Data Sources: Your computer’s files, databases, and services that MCP servers can securely access
  • Remote Services: External systems available over the internet (e.g., through APIs) that MCP servers can connect to

​
Get started

Image for: ​Get started

Choose the path that best fits your needs:

​
Quick Starts

For Server Developers

Image for: For Server Developers

Get started building your own server to use in Claude for Desktop and other clients

For Client Developers

Image for: For Client Developers

Get started building your own client that can integrate with all MCP servers

For Claude Desktop Users

Image for: For Claude Desktop Users

Get started using pre-built servers in Claude for Desktop

​
Examples

Example Servers

Image for: Example Servers

Check out our gallery of official MCP servers and implementations

Example Clients

Image for: Example Clients

View the list of clients that support MCP integrations

​
Tutorials

Image for: ​Tutorials

Building MCP with LLMs

Image for: Building MCP with LLMs

Learn how to use LLMs like Claude to speed up your MCP development

Debugging Guide

Image for: Debugging Guide

Learn how to effectively debug MCP servers and integrations

MCP Inspector

Image for: MCP Inspector

Test and inspect your MCP servers with our interactive debugging tool

MCP Workshop (Video, 2hr)

Image for: MCP Workshop (Video, 2hr)

​
Explore MCP

Image for: ​Explore MCP

Dive deeper into MCP’s core concepts and capabilities:

Core architecture

Image for: Core architecture

Understand how MCP connects clients, servers, and LLMs

Resources

Image for: Resources

Expose data and content from your servers to LLMs

Prompts

Image for: Prompts

Create reusable prompt templates and workflows

Tools

Image for: Tools

Enable LLMs to perform actions through your server

Sampling

Image for: Sampling

Let your servers request completions from LLMs

Transports

Image for: Transports

Learn about MCP’s communication mechanism

​
Contributing

Image for: ​Contributing

Want to contribute? Check out our Contributing Guide to learn how you can help improve MCP.

​
Support and Feedback

Image for: ​Support and Feedback

Here’s how to get help or provide feedback:

  • For bug reports and feature requests related to the MCP specification, SDKs, or documentation (open source), please create a GitHub issue
  • For discussions or Q&A about the MCP specification, use the specification discussions
  • For discussions or Q&A about other MCP open source components, use the organization discussions
  • For bug reports, feature requests, and questions related to Claude.app and claude.ai’s MCP integration, please see Anthropic’s guide on How to Get Support