A.I. Learns to Write in DNA
Scientists prompted A.I. to design and create new viruses for the first time, a milestone for medicine that also raises new biosecurity concerns.
Model Context Protocol Gets a Usability Upgrade
By Prompt AI News1 min read
#mcp#developer tools#ai agents
As TechCrunch first reported, the Model Context Protocol — the open standard that lets AI agents connect to external data sources and tools — is receiving a significant usability overhaul built around a new stateless approach to session management. For developers who have tried and abandoned MCP implementations, the change directly addresses the most common complaint: that MCP demanded too much state-tracking overhead compared to how standard web APIs are typically designed.
MCP matters because it defines how AI agents reach beyond their training data — pulling live information from databases, files, calendars, and third-party services. More capable and reliable agents depend on well-implemented MCP connections, but the protocol's complexity has kept adoption narrower than its backers hoped.
The new stateless session model brings MCP architecture closer to REST and other familiar API patterns, reducing the specialist knowledge required to build a working implementation. That lowers the bar meaningfully for developers who are not protocol experts but want to build agents that interact with real-world data.
Whether adoption follows will depend on how quickly toolchains, SDKs, and documentation catch up to the updated spec.
Leave a Comment
All comments are reviewed before appearing. Keep it respectful.
More in Commentary
View all →Rules....There are No Rules
The Trump administration has no idea on how to handle open-source and open-weight AI models from China.
Google's AI Talent Exodus Mounts as Company Centralizes Leadership in California
Google is consolidating AI leadership in California but the reorganization is pushing out the engineers who built its AI division