Posts tagged "model-context-protocol"
Google Goes All-In on MCP With Managed Servers Across Cloud and Maps
Google just made every major cloud service agent-ready by launching fully managed MCP servers. Here's what changed, which services are covered, and why it matters for the AI agent infrastructure space.
Anthropic's Code Execution With MCP Cuts Agent Token Usage by 98.7%
Anthropic published a new engineering approach that turns MCP tool calls into code APIs, dropping token consumption from 150,000 to 2,000. Here's how it works, why it matters, and what it means for anyone building AI agents at scale.
Anthropic Donates MCP to Linux Foundation's New Agentic AI Foundation
Anthropic hands the Model Context Protocol to a new Linux Foundation body co-founded with OpenAI and Block. Here's what the Agentic AI Foundation means for the future of AI interoperability, who's backing it, and why it matters now.
AI Agents Remember Everything, And That's a Privacy Problem
AI agents using the Model Context Protocol now share memory across services. A New America brief exposes the privacy gaps, security risks, and power dynamics that current laws can't handle, and proposes what to do about it.