Skip to content

Glossary · Updated Sep 24, 2026

Model Context Protocol (MCP)

The Model Context Protocol is an open standard that lets an AI application connect to external data sources and tools through one common interface instead of a custom integration per source.

Anthropic introduced MCP in November 2024 as an open, freely available standard, and other AI vendors and developer tools have since adopted it. Before MCP, connecting an AI assistant to a company's files, databases or business apps meant writing a separate integration for each combination of AI tool and data source. MCP standardizes that connection so a data source built once can work with any MCP-compatible AI application.

The common misconception is that MCP is itself an AI model or an agent. It is a connection standard, similar in spirit to how a USB port standardizes connecting a device rather than doing the device's job. MCP still depends on the permissions and access controls placed around each connection, so a company adopting it needs to decide what each connected source is allowed to expose.

Bring us a workflow.

Tell us where the work slows down. We will help you see where to start.

Request a discovery call