AI Dictionary › AI Fundamentals
The Model Context Protocol (MCP) is an open standard for connecting AI models to external tools, data sources and systems through a single, uniform interface. Instead of writing a custom integration for every database, API or file system, a developer exposes them once through MCP and any compatible AI application can use them. It is often described as the USB-C of AI integrations.
MCP follows a client-server design. The application hosting the model runs one or more MCP clients, and each client connects to an MCP server that exposes three kinds of capabilities: resources (data the model can read), tools (functions the model can call) and prompts (reusable instruction templates). The model requests a tool or resource, the server runs it in a controlled way, and the result is returned into the model context.
MCP lets an assistant read a company knowledge base, query a live database, open files, call internal APIs or drive another application, all without bespoke glue code. Because the protocol is shared, a tool built once works across every MCP-aware product, which is what makes it valuable for agents that must act in the real world.
MCP was introduced by Anthropic in November 2024 and released as an open specification. Through 2025 it was adopted well beyond its origin, becoming a common way to standardise how models connect to tools and a building block of the agentic wave.
From our network
INDACO TMS: Transport Management for European Logistics
Shipment tracking, multi-carrier EDI and automated invoicing in one cloud platform. Invoices generated in under 10 seconds.
Visit indacotms.com →From the Agora Intelligence blog
📱 Download the Android app (beta) iOS coming soon
Say what you mean. Get what you need.
Grace Certified, the AI coach that trains and certifies your prompt engineering, by Agora Intelligence.