Glossary · 5 · Building with AI: APIs, tools and agents
Model Context Protocol (MCP)
Also known as: MCP, MCP server
The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in 2024 and since adopted widely across the industry, that defines how AI applications connect to external tools and data sources through MCP servers, so one integration works with many AI clients.
- Expert
- Technical writers
- Technical project managers
- Developers
In one sentence
Model Context Protocol (MCP) explained: the open standard for connecting AI assistants to tools and data — and why documentation teams care.
Example
A documentation team runs an MCP server that exposes search over its published topics; writers and developers can query it from any MCP-enabled assistant or coding tool.
Explained in context
Context cards connect this term with others to answer one question. Also in British English and German.
Why it matters on your learning path
- Technical writers: An MCP server over your documentation makes it directly usable in developers’ AI tools — a new delivery channel.
- Technical project managers: MCP reduces integration effort but adds new access paths to company data; include servers in security reviews.
- Developers: Build MCP servers for your systems once instead of custom plugins per AI tool; apply least privilege to every exposed tool.