What is MCP (Model Context Protocol)?

Updated Oct 26, 2026 · Sources listed at the end

MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems: data sources such as files and databases, tools such as search engines, and workflows such as reusable prompts. The project’s own analogy is “a USB-C port for AI applications”.¹

Who created it

Anthropic open-sourced MCP on 25 November 2024 as “a new standard for connecting AI assistants to the systems where data lives”. The launch included the specification and SDKs, local MCP server support in the Claude Desktop apps, and an open-source repository of servers for systems such as Google Drive, Slack, GitHub, Git, Postgres and Puppeteer.²

How it works

Developers either expose data through an MCP server or build AI applications (MCP clients) that connect to servers.² A coding agent acting as a client can then, for example, read issues from GitHub or query a database without custom integration code.

MCP in coding tools

• Claude Code adds servers with claude mcp add, for example claude mcp add --transport http notion https://mcp.notion.com/mcp.³ See Claude Code MCP setup.
• Cursor installs servers from its marketplace or from an mcp.json file.⁴ See Cursor MCP setup.
• GitHub publishes an official GitHub MCP server.

Our MCP-capable coding tools list shows which tools mention MCP on their own pages.

A security note

Claude Code’s documentation warns: verify you trust each server before connecting it, because servers that fetch external content can expose you to prompt injection.³

Tools mentioned

• Claude Code: paid from $20/mo
• Cursor: free plan, paid from $8/mo
• Cline: free plan, paid from Free
• GitHub Copilot: free plan, paid from $10/mo

Sources

1. Model Context Protocol: What is MCP?
2. Anthropic: Introducing the Model Context Protocol (25 Nov 2024)
3. Claude Code docs: Connect Claude Code to tools via MCP
4. Cursor docs: Model Context Protocol