Topic
Cloudflare
8 episodes
-
MCP server portals
Asteria and Draco unpack Cloudflare's MCP server portals as boundary infrastructure for enterprise MCP adoption: one Access-controlled endpoint, curated tools, managed OAuth, Code Mode, and observability, with caveats around direct server URLs, admin credentials, and sync paths.
-
Introducing Precursor: detecting agentic behavior with continuous client Side signals
Fern and Lintel dig into Cloudflare’s Precursor, a session-level bot detection layer that watches behavior across the whole journey instead of only at challenge points. They focus on the real argument: modern automation can fake isolated moments, but it’s much harder to fake a consistent human rhythm over time.
-
Your Worker can now have its own cache in front of it
Cloudflare launched Workers Cache, a tiered cache that sits in front of Worker code itself — not between the origin and Cloudflare. Single-line Wrangler config plus standard Cache-Control headers. On hit, Worker doesn't run (zero CPU cost); on miss, Worker runs and populates cache for the next request anywhere on Earth. The shift: Workers went from 'bolt-on transformation layer in front of origin' (2017) to 'the origin itself' (modern frameworks: Astro, Next.js, Remix, SvelteKit). Cache-in-front solves the SSR problem — server-render on demand, cache the response, refresh on TTL without build-time prerender cost. Stale-while-revalidate makes it feel instant (serve stale immediately, refresh in background). Full Vary support for content negotiation (same URL, multiple representations: WebP vs JPEG, English vs French, HTML vs JSON). Per-entrypoint cache control lets you compose caching into app structure. Available today to all Workers on any plan.
-
AI agents get their own phone directory built atop DNS
Cody and Justy dig into DNS-AID, a new Linux Foundation project that lets AI agents discover each other using DNS records instead of hardcoded configs. Cody's skeptical the world needed another spec layer; Justy thinks the infrastructure bet is actually smart. They work through what it does, what it doesn't solve, and whether the McKinsey trillion-dollar number means anything at all.
-
Cloudflare Completes Its Agent Infrastructure Stack with Browser Run Rebuild and Six Layer Platform
Justy and Cody dig into Cloudflare's rebuilt Browser Run and the six-layer agent infrastructure stack it anchors. They debate whether the "most complete agent platform outside the hyperscalers" claim holds up, unpack the D1/Queues migration and 500k container capacity numbers, and argue about what "most complete" actually means for developers choosing a platform.
-
Cloudflare Launches Code Mode MCP Server to Optimize Token Usage for AI Agents
Cloudflare's new Model Context Protocol (MCP) server powered by Code Mode reduces token usage for AI agents, making it possible to interact with complex APIs more efficiently.
-
Cloudflare’s new Dynamic Workers ditch containers to run AI agent code 100x faster
Cloudflare launches Dynamic Workers, ditching containers for millisecond-starting isolates that run AI agent code 100x faster. The tech enables 'Code Mode' — where LLMs write TypeScript functions instead of chaining tool calls, cutting token usage by 81%. Built on V8 isolates, it's positioning sandboxing as a strategic layer in the AI stack.
-
Introducing Moltworker: a self hosted personal AI agent, minus the minis
In this episode, we explore Moltworker, a self-hosted personal AI agent that operates seamlessly on Cloudflare's infrastructure. We discuss its implications for privacy, the power of self-hosting, and how it simplifies AI integration for everyday users.