Google adopts Anthropic AI’s MCP standard

Google DeepMind has said that they will be adding support for Model Context Protocol, a standard released by Anthropic AI that connects LLM applications with tools. CEO Demis Hassabis made the announcement on X saying that MCP was quickly becoming accepted as a common protocol with AI agents around. 

A few weeks ago, Anthropic rival OpenAI also said they would be adopting MCP across their products including the desktop app, ChatGPT. 

MCP essentially allows AI models to draw data from sources like business tools or software or even a database. This helps developers to build a seamless connection between data sources and AI applications like chatbots while also helping AI models generate better and more relevant responses. 

The standard is becoming mainstream due to the arrival of AI agents. As developers build more AI agents that could tie up multiple tasks together, MCP could prove to be useful. 

Developers can build MCP clients or MCP servers for AI applications and workflows so that they can be connected to them on command.

Anthropic open-sourced MCP last year in November. Since then, companies like Block, Replit, Apollo and Codeium have all integrated it for their platforms.