Several weeks after OpenAI announced its decision to integrate Anthropic’s standard for linking AI models to data systems, Google has decided to do the same. On Wednesday, Demis Hassabis, CEO of Google DeepMind, revealed in a statement on social media platform X that Google plans to incorporate Anthropic’s Model Context Protocol (MCP) into its Gemini models and Software Development Kit (SDK). However, no specific timeframe was provided for the implementation.
Hassabis described MCP as an effective protocol, which is swiftly becoming a widely accepted open standard within the AI industry. He expressed eagerness to continue its development in collaboration with the MCP team and other stakeholders in the sector.
MCP facilitates the integration of models with data sources such as business tools and software, enhancing their capability to perform tasks. It connects to content repositories and application development environments, allowing developers to establish two-way communication between data sources and AI-driven applications like chatbots.
Developers have the option to utilize “MCP servers” to make data accessible and to create “MCP clients,” such as applications and workflows, that can interact with these servers as needed. Since Anthropic open-sourced MCP, several companies, including Block, Apollo, Replit, Codeium, and Sourcegraph, have adopted MCP support for their platforms.