OpenAI to Adopt Anthropic Standards for Connecting AI Models with Data

OpenAI has announced its support for the Model Context Protocol (MCP) standard proposed by its competitor Anthropic, aiming to connect AI assistants with data storage systems.

OpenAI CEO Sam Altman stated on the X platform on Wednesday that the company will incorporate MCP support into its products, including the ChatGPT desktop application. MCP is an open-source standard designed to help AI models generate more accurate and relevant responses to specific queries.

The MCP enables models to extract information from various data sources such as business tools, software, content repositories, and application development environments to complete tasks. This protocol allows developers to establish a two-way connection between data sources and AI-driven applications like chatbots.

Developers can expose data through "MCP servers" and build "MCP clients" (such as applications and workflows), which can connect to these servers based on commands. Since Anthropic open-sourced MCP, several companies, including Block, Apollo, Replit, Codeium, and Sourcegraph, have added MCP support to their platforms.

Anthropic's Chief Product Officer, Mike Krieger, welcomed OpenAI's adoption of MCP on the X platform. He emphasized that MCP has become a thriving open standard with thousands of integrations and continues to grow. He noted that large language models (LLMs) perform best when connected to users' existing data and software.

OpenAI stated that more details about its MCP plans will be shared in the coming months.