MCP’s Exposed Core: How a Protocol Built for AI Agents Became a Security Liability

Anthropic defined the standards inside Agent Plugins. So why isn’t it helping govern the format?

Earlier this month, Vercel released Agent Plugins 1.0.0 with core maintainers from AWS, Cursor, Microsoft, and OpenAI. Google announced the same day that it was joining them. The format fixes something that genuinely annoys developers: A skill and an MCP server that work fine on their own still have to be forked and maintained twice the moment you ship them to a second client. Though the six companies agreed on where components live, they don’t …

MCP’s Exposed Core: How a Protocol Built for AI Agents Became a Security Liability

Developers once saw the Model Context Protocol as the missing link for smarter AI. It let large language models reach into tools, data sources and external services with a standard set of instructions. Adoption exploded. Yet that speed has now exposed cracks that security teams cannot ignore. More than 21,000 internet-facing MCP server instances sit exposed today. Nearly 92 percent of audited production servers lack basic OAuth authentication. T…

Google-backed agentic A2A protocol gets a new home

The Agent2Agent Protocol (A2A), a Google-created standard for AI agents to talk to one another, is moving to the Agentic AI Foundation, backers of the emerging standard told Axios. Open standards could make it easier to mix AI agents and tools from different providers without building custom connections between each one. Different companies build AI […] The post Google-backed agentic A2A protocol gets a new home appeared first on OODAloop.

How MCP Servers Can Expose Enterprise Secrets

MCP servers can expose enterprise secrets through plaintext configuration files, over-permissioned access and prompt injection, often before security teams even know the server is running. As more organizations adopt AI agents into their systems, that exposure can silently become a major gap in MCP server security. The Model Context Protocol (MCP) allows AI agents to reach the tools and data,