Short answers, pulled from the story.
Anthropic unveiled the Model Context Protocol in November 2024. This announcement addressed the chaotic landscape where every new AI tool required a unique custom-built bridge to connect with existing software.
The Model Context Protocol draws heavily from the Language Server Protocol and transports data over JSON-RPC 2.0. This architecture enables bidirectional connections that allow data sources to push information to AI tools and vice versa.
By March 2025, OpenAI had officially adopted the Model Context Protocol and integrated it across its products including the ChatGPT desktop application. Google DeepMind and Cloudflare also provided support, while integrated development environments like Replit and code intelligence tools such as Sourcegraph adopted the protocol.
In April 2025, security researchers identified critical vulnerabilities including prompt injection attacks that could manipulate AI into executing unintended commands. The analysis also revealed that tool permissions allowed for the combination of different tools to exfiltrate sensitive data and that lookalike tools could silently replace trusted ones.
Anthropic donated the Model Context Protocol to the Agentic AI Foundation in December 2025. This foundation operates as a directed fund under the Linux Foundation and was co-founded by Anthropic, Block, and OpenAI.