🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

"How do we build these microservice architectures and serverless apps?" Brian Rinaldi joined Nick Taylor to discuss LocalStack, an open-core tool that lets developers run a complete AWS cloud environment on their laptop for faster, cost-effective development and testing.

OAuth ≠ secure by default. Proxy-enforced OAuth is mandatory, not optional What do MCP Security Best Practices actually require and where are current implementations are falling short? Find your answers on Nick Taylor's latest The New Stack piece: thenewstack.io/the-model-cont…

Let's Explore Langflow x.com/i/broadcasts/1…

AX + MCP + Netlify x.com/i/broadcasts/1…

Traditional security models weren't built for autonomous agents. Our latest guide breaks down: → Why MCP changes the security model → How Zero Trust protects agent actions in real time → What to do before connecting LLMs to internal tools Read more: bit.ly/4k2TrsF.

Asana’s MCP bug exposing cross-tenant data serves as a warning. Things can go wrong when: → OAuth is treated as authorization → Agent access isn’t scoped or audited → No enforcement layer stands between the agent and the system Implement guardrails: bit.ly/3TJPPAU

Zero Trust is about reducing attack surface, enforcing least privilege, and continuously reevaluating risk. NIST SP 1800-35 is a a how-to Zero Trust manual based on real technologies, open standards, and 19 implementation builds. Read its key takeaways: bit.ly/3TfcpBl

There's a lot to keep up within the Model Context Protocol (MCP) space, but it's clear that MCP is here and needs to be secured. We’ve compiled June 2025's MCP incidents, industry news, blogs, and other reports. Find it here: bit.ly/4exZvIz

Discuss Event-Driven Architecture for AI Agents Abhi, Head of Developer Advocacy (EMEA/APAC) at DigitalOcean, joins Nick Taylor to discuss event-driven architecture for AI Agents. Join us on Wednesday, July 16 at 9AM ET: youtube.com/watch?v=-ai4ja…

Your team is already sharing sensitive internal data with AI, and these AI agents must be bounded by proper guardrails. Our latest post breaks down: • “Shadow AI" • How to build a secure, low-friction LLM gateway • Real-world case studies Read more: bit.ly/4ny8gpM

A Claude-based IDE with root-level database access was tricked into exfiltrating secrets—just by reading a support ticket. One convincing prompt was all it took. What went wrong, why Row-Level Security (RLS) failed, and what defenses can actually work: bit.ly/4kw6LpJ