Article in The New Stack by Eric Newcomer
In a roundtable panel at the MCP Dev Summit last week in New York, Model Context Protocol (MCP) maintainers from Anthropic, AWS, Microsoft, and OpenAI reassured us that the MCP spec is in safe hands at the Agentic AI Foundation (AAIF) and will be addressing critical enterprise requirements for security, reliability, and governance.
Starting in December with contributions of MCP, goose, and AGENTS.md, the AAIF has quickly grown to 170 members. MCP is the most popular project and has become the industry standard for connecting AI agents to data and applications.
The panel reassured MCP users that little has changed in how the project governs itself (it’s still a bottom-up, open source project). The AAIF provides a connection to enterprise users and their needs, which feeds back into protocol development to address concerns about using MCP in production.
The broad adoption of MCP has identified significant areas for improvement, they said, especially for enterprise applications requiring strict security, scalability, reliability, and governance.
Click here to read the article in Chinese.
