Model Context Protocol (MCP)
MCP is an open standard from Anthropic (2024) letting AI agents uniformly use external tools, databases and services.
MCP solves the 'N×M' integration problem: without a standard each AI client must integrate separately with each tool. With MCP a tool builds one MCP server and any MCP-compatible system (Claude Desktop, Claude Code, more IDEs and apps) can use it directly. Rapidly adopted since 2024 launch by Anthropic ecosystem and increasingly beyond — key to scalable AI tooling.
Example
A SaaS builds one MCP server exposing their API. Users can log in via Claude Desktop, query data and perform actions — without the SaaS building its own Claude integration.
Frequently asked questions
How do I build an MCP server?
Official SDKs in TypeScript, Python and others. For simple tools: <50 lines of code. Docs on modelcontextprotocol.io.
Related terms
Further reading
- → Our service: AI sector