MCP App StoreThe latest from the AI and MCP ecosystem, curated daily.
Sources
OpenAI has implemented built-in safeguards to prevent prompt injection and data exfiltration when AI agents interact with external URLs. This is a critical security update for those building agentic workflows.
OpenAI has launched Prism, a free LaTeX-native workspace featuring integrated GPT-5.2. It aims to streamline academic research by combining writing, collaboration, and reasoning in a single environment.
A technical breakdown of the Codex agent loop, detailing how the Codex CLI manages models and prompts via the Responses API. Essential reading for those building agentic CLI tools.
OpenAI shares their architecture for scaling PostgreSQL to handle millions of queries per second. The system leverages a combination of replicas, aggressive caching, and workload isolation to maintain performance for 800 million users.
OpenAI launches ChatGPT Go, providing worldwide access to the GPT-5.2 Instant model. It features higher usage limits and expanded memory to make advanced AI more accessible and affordable globally.
OpenAI introduces enterprise-grade AI for healthcare, focusing on HIPAA compliance and reducing administrative burden in clinical workflows.
A showcase of a voice-first AI companion leveraging GPT-5.1. It focuses on low-latency responses and memory-driven personalities for natural, real-time conversations.
OpenAI launches ChatGPT Health, a secure experience that integrates personal health data and apps. The feature emphasizes physician-informed design and strict privacy protections.
OpenAI is utilizing automated red teaming and reinforcement learning to proactively identify and patch prompt injection vulnerabilities in ChatGPT Atlas. This is critical for the stability and security of AI agents interacting with browser environments.
OpenAI presents a framework for monitoring internal chain-of-thought reasoning in AI models. The research indicates that observing internal reasoning is more effective for scalable control than monitoring final outputs alone.
OpenAI released a system card addendum for GPT-5.2-Codex, detailing the technical specifications and safety evaluations for the coding-specialized model variant.
OpenAI released GPT-5.2-Codex, featuring advanced long-horizon reasoning and large-scale code transformation capabilities. It specifically targets complex software engineering tasks and cybersecurity enhancements.
OpenAI has launched a directory for ChatGPT apps, allowing developers to submit their tools for review and publication. An updated Apps SDK and new guidelines are provided to help build chat-native experiences with real-world actions.
OpenAI introduces a new evaluation framework to measure AI's impact on biological wet-lab research. The study utilizes GPT-5 to optimize molecular cloning protocols, highlighting both potential efficiency gains and safety risks.
OpenAI has launched an upgraded image generation model for ChatGPT and the API as GPT-Image-1.5. The new model offers faster generation speeds (up to 4x) and improved precision in edits and consistency.
OpenAI detailing the rapid development of Sora for Android using Codex. Highlights how AI-assisted planning and parallel coding accelerated the shipping timeline to just 28 days.
Introduction of GPT-5.2, OpenAI's most capable model for mathematics and science. The model achieves new state-of-the-art results on benchmarks like GPQA Diamond and FrontierMath.
OpenAI has released GPT-5.2, a frontier model optimized for professional work. It features significant improvements in reasoning, coding, and vision to support more reliable agentic workflows via API and ChatGPT.
OpenAI and Disney have partnered to bring over 200 iconic characters to Sora for fan-inspired short videos. The deal also includes the adoption of ChatGPT Enterprise and the OpenAI API across Disney's company.
OpenAI has co-founded the Agentic AI Foundation under the Linux Foundation, donating the AGENTS.md standard. This initiative aims to establish open, interoperable standards for the safe development and deployment of agentic AI systems.