AiNews.com
Posts
OpenAI Adopts Anthropic’s MCP Standard to Connect AI Models to Data

OpenAI Adopts Anthropic’s MCP Standard to Connect AI Models to Data

Alicia Shapiro
March 27, 2025 • Estimated Reading Time: 5 minutes

A digital illustration of two futuristic AI platforms labeled “OpenAI” and “Anthropic,” connected by a glowing data stream representing the MCP protocol. Developers work in the background on code and enterprise software, while chatbots and AI assistants interact on nearby screens. The scene emphasizes real-time interoperability and seamless integration between AI systems and business data.

Image Source: ChatGPT-4o

OpenAI Adopts Anthropic’s MCP Standard to Connect AI Models to Data

OpenAI has announced it will support the Model Context Protocol (MCP)—an open-source standard created by rival AI company Anthropic—across its core products, including ChatGPT’s desktop app and its Agents SDK.

The move reflects a broader trend in the AI industry toward interoperability, where models are enhanced by seamless access to enterprise tools, software environments, and proprietary data. By integrating MCP, OpenAI enables its models to draw from richer, real-time context—improving relevance, accuracy, and task execution in dynamic workflows.

What Is MCP and Why It Matters

MCP is a technical protocol that allows developers to create two-way connections between AI models and data environments. It enables:

Secure access to business systems, content repositories, and dev environments
Streamlined integration between LLM-powered assistants and enterprise tools
Real-time responsiveness based on up-to-date internal or user-defined data

With MCP, developers can host MCP servers to expose data and build MCP clients—such as chatbots or AI agents—that query and interact with those data sources on demand.

Originally developed by Anthropic, MCP has already seen adoption from companies like Block, Apollo, Replit, Codeium, and Sourcegraph, signaling strong community momentum.

“People love MCP and we are excited to add support across our products,” said OpenAI CEO Sam Altman on X. “It’s available today in the Agents SDK, with support for the ChatGPT desktop app and Responses API coming soon!”

Screenshot of an X post from the official OpenAI Developers account, announcing that users can now connect Model Context Protocol (MCP) servers to the OpenAI Agents SDK. The post includes a link to documentation and mentions that MCP support for the OpenAI API and ChatGPT desktop app is in development, with more updates to be shared in the coming months.

Image Source: OpenAI Developers X Post

Collaboration in a Competitive Landscape

Anthropic’s Chief Product Officer Mike Krieger welcomed the announcement, writing:

“Excited to see the MCP love spread to OpenAI – welcome! MCP has become a thriving open standard with thousands of integrations and growing. LLMs are most useful when connecting to the data you already have and software you already use.”

OpenAI says it will share more details about its MCP integration plans in the coming months.

Screenshot of an X post by Mike Krieger, Chief Product Officer at Anthropic, expressing excitement about OpenAI adopting the Model Context Protocol (MCP). He notes MCP has grown from a concept to a thriving open standard with thousands of integrations. Krieger emphasizes that large language models are most useful when connected to existing software and data. Below his post is a quoted X post from Sam Altman, CEO of OpenAI, announcing that MCP support is being added across OpenAI products, including the Agents SDK, with ChatGPT desktop and Responses API support coming soon.

Image Source: Mike Krieger X Post

What This Means

This marks a notable step in cross-platform alignment between two of the industry’s leading AI developers. By adopting Anthropic’s MCP standard, OpenAI not only boosts its product functionality but signals a shift toward shared infrastructure in the generative AI ecosystem.

For developers and enterprise users, this means faster deployment of intelligent agents that can access critical systems, act on relevant data, and generate more contextualized outputs. As MCP gains traction, the lines between AI models and business tools will continue to blur—making integration the next competitive frontier in AI development.

Editor’s Note: This article was created by Alicia Shapiro, CMO of AiNews.com, with writing, image, and idea-generation support from ChatGPT, an AI assistant. However, the final perspective and editorial choices are solely Alicia Shapiro’s. Special thanks to ChatGPT for assistance with research and editorial support in crafting this article.