Model Context Protocol (MCP) is an open standard created by Anthropic that lets AI models connect to external tools, data sources, and APIs through a unified interface.
Model Context Protocol (MCP) is an open standard created by Anthropic that lets AI models connect to external tools, data sources, and APIs through a unified interface. Think of it as a USB-C port for AI — one standard protocol that works everywhere. MCP servers expose capabilities like file access, database queries, or web browsing, and AI clients can discover and use them automatically.
Before MCP, every AI integration was a custom one-off. If you wanted Claude to read your files, you'd build a specific integration. If you wanted it to query a database, that's another custom setup. MCP standardizes this so any compatible AI model can connect to any compatible tool. It uses a client-server architecture where the AI model is the client and tools are servers that advertise their capabilities.
A developer sets up an MCP server for their company's database. Now any MCP-compatible AI assistant can query that database without custom code — just connect and go.
Browse our complete glossary or subscribe to our newsletter for the latest AI news and insights.