OpenAI Agents Now Compatible with Competitor Anthropic’s Protocol

OpenAI has introduced support for Anthropic’s Model Context Protocol, an open-source standard that connects AI applications to data sources. This allows developers to ensure their chatbots respond only with relevant information.

On Wednesday, OpenAI CEO Sam Altman shared the news on X, stating that the protocol is now available in the Agents SDK—a toolkit for building AI-driven agents. The team at OpenAI is also working on integrating this support into the ChatGPT desktop app and OpenAI API, with more announcements expected in the coming months.

So, how does MCP enhance AI’s access to data? Scaling AI models often becomes complex because they need up-to-date access to various third-party data sources, like cloud servers and business platforms. Each source uses its own tech language, which means developers usually have to create custom integrations for every one of them.

MCP acts like a universal language, enabling two-way communication between various AI models and different data sources. This makes it easier and more reliable for AI systems to get the data they need, according to Anthropic.

For developers using the Agents SDK, they can expose their data through “MCP servers” or create “MCP clients,” which are apps that can easily connect to those servers. This development cuts down on the need for custom integrations and helps AI access information across tools without losing context.

Anthropic’s Chief Product Officer, Mike Krieger, expressed his enthusiasm about OpenAI adopting MCP in a post on X, highlighting that large language models are most effective when they link to existing data and software.

Since MCP became open-source in November, several AI platforms have jumped on board, including Microsoft Copilot, Apollo, Replit, Codeium, and Sourcegraph.

Just a week ago, Microsoft announced MCP support in Copilot Studio, allowing users to connect their agents to MCP servers directly. Following OpenAI’s announcement, Microsoft also released a Playwright MCP server on GitHub, enabling MCP agents to interact with the web through functions like clicking and typing.

The growing adoption of MCP by various AI companies boosts its value within the community. With OpenAI on board, Anthropic may be setting the stage for a global standard in agent interconnectivity.

Unlock your business potential with our expert guidance. Get in touch now!

silenced-gagged-secret-Michael-adobe.jpg

Post Office Criticized for Deleting Comments on IT Scandal from Social Media

Whitehouse-fotolia-scaled.jpg

When Leaders Overlook Cybersecurity Guidelines, the Entire System Suffers

Police-crime-2-adobe.jpg

Police Digital Service Board Director Resigns Months After CISO’s Departure

surveillance-CCTV-facial-recognition-Gorodenkoff-adobe.jpg

Essex Police Reveals ‘Incoherent’ Facial Recognition Evaluation

chatbot-1-fotolia.jpg

Podcast: RSA 2025 – Navigating AI Risks and the CISO’s Role

hybrid-cloud-storage-fotolia.jpg

Trump’s Visit Strengthens Saudi Arabia’s AI Initiatives

threat-management-fotolia.jpg

Security Tests Uncover Major Vulnerability in Government’s One Login Digital ID System