Agents & tools
MCP
Model Context Protocol — an open standard that lets AI models connect to external tools and data sources in a consistent way.
01 ——
In plain English
Model Context Protocol (MCP) is an open standard created by Anthropic that defines how AI models talk to external tools, APIs, and data sources. Instead of every AI app building its own custom integrations, MCP provides a single, consistent protocol — like a USB-C port for AI.
What MCP enables:
- An AI model can read your local files, query a database, or call an API
- Tool builders write one MCP server; any MCP-compatible AI can use it
- Users can give AI assistants access to their own tools and data safely
Why it matters: Before MCP, every AI app had to hand-code integrations with every tool. MCP makes AI extensibility composable and standardised, similar to how HTTP standardised the web.
MCP is supported by Claude, and is being adopted across the AI ecosystem.
02 ——
Related terms
Agent
An AI system that can take actions, use tools, and make decisions autonomously to complete a goal.
Tool Use
The ability of an AI model to call external tools — like a calculator, search engine, or API — to help answer a question.
Function Calling
A feature that lets an AI model trigger specific functions or APIs in your app instead of just returning text.
API
An interface that lets developers send requests to an AI model and get responses programmatically — the way most AI tools talk to LLMs.
Back to glossaryLast reviewed May 2026