Glossary › Agents

MCP (Model Context Protocol)

Open standard by Anthropic for connecting AI models to external tools, resources, and data sources. Defines a JSON-RPC protocol for servers to expose capabilities to any MCP-compatible client.

Where this is taught

• MCP Protocol — Connecting Agents to External Systems — Phase 5: AI Agents in Workflows
• MCP Security & Computer Use / Browser Agent Safety — Phase 4: RAG & Agent Security
• MCP and Tool Integration Architecture — Phase 5: Agent Orchestration Patterns
• What MCP Is and Why It Matters — Phase 5: Model Context Protocol (MCP)
• Building MCP Servers — Phase 5: Model Context Protocol (MCP)
• Dynamic Tool Discovery & MCP Registries — Phase 5: Model Context Protocol (MCP)

Related terms

Tool Use · Agent · Function Calling

More in Agents

Agent · ReAct · Tool Use · Multi-Agent System · Orchestration · Sandboxing

Learn this by building

DeVenture Academy teaches AI engineering through projects — every lesson is paired with a hands-on lab you run on your own machine with real tools.

Create a free account — the opening phases of 24 of 30 courses are free, no credit card. Or see Pro pricing.

All courses · Pricing · About · FAQ · Glossary