Model Context Protocol (MCP)
The Model Context Protocol is an open standard that lets AI assistants connect to external tools and data sources through a uniform interface. An MCP server exposes typed tools and resources that a model client can discover and call, so capabilities can be added without bespoke per-integration code.
Synonyms: MCP, model context protocol, MCP server, tool protocol
The Model Context Protocol standardizes how a language model reaches beyond its own context to use tools and read data. Instead of writing a custom adapter for every assistant, a platform runs an MCP server that publishes typed tools and resources with schemas and annotations. A compliant client discovers those capabilities and invokes them through one consistent contract. For governed work automation, MCP is valuable precisely because it is structured: every tool call arrives schema-described, which makes it possible to validate inputs, enforce tenant scoping, and subject the call to the same approval policy as any human-initiated action.