>_TheQuery
← Glossary

MCP

Agents

Model Context Protocol - an open standard created by Anthropic that defines how AI assistants connect to external data sources, tools, and services through a unified interface.

MCP (Model Context Protocol) is an open standard announced by Anthropic in November 2024 that provides a standardized way for AI models to connect to external data sources, tools, and services. It defines a common protocol so that any AI assistant can interact with any compatible data system, eliminating the need for custom integrations between every model and every tool.

MCP follows a client-server architecture. An AI application acts as an MCP client, while external services expose their capabilities through MCP servers. The protocol defines how tools, resources, and prompts are discovered, invoked, and how results are returned. This means a single MCP server built for a database, a code repository, or a business application can work with any AI assistant that speaks MCP, regardless of which model powers it.

MCP achieved rapid industry adoption throughout 2025. OpenAI integrated it across its products including the ChatGPT desktop app in March 2025, and Google DeepMind confirmed support for Gemini models shortly after. The specification received major updates in November 2025, adding asynchronous operations, statelessness, and an official registry for discovering MCP servers. In December 2025, Anthropic donated MCP to the Agentic AI Foundation under the Linux Foundation, co-founded with Block and OpenAI, cementing it as a vendor-neutral industry standard rather than a proprietary protocol.

Last updated: February 26, 2026