I’m Tim Benniks, Developer Experience and Product Leader at Contentstack. I build developer tools and write about AI engineering, composable architecture, and what makes software useful.
The journal
Essays on developer experience, AI-accelerated engineering, and the platforms that hold it all up.
How the new MCP Skills Extension works, from skill discovery and on-demand loading to content verification, workflow guidance, and managed profiles.
This article argues that a single, monolithic MCP server per platform is the wrong abstraction, especially for complex systems like Contentstack. Instead, it introduces managed profiles as the right unit of configuration, aligned to jobs, teams, or access boundaries rather than product catalogs. Each managed profile bundles a curated set of tools, Automations, and agents, enriched with account context, while still respecting individual user identities and permissions. Profiles can only narrow what a user can do, never expand their underlying platform permissions. This makes configurations easier to reason about, review, audit, and replicate across environments, and offers a scalable pattern for enterprise platforms with many roles and capabilities.
Introducing MCP Profile Hub. I explain why enriching tool definitions with tenant-specific context dramatically improves agent performance. Instead of exposing generic CMS tools that force models to discover content types, environments, locales, and branches through multiple lookup calls, Profile Hub injects real account data directly into JSON Schemas as enums, defaults, and descriptions. This reduces tool calls, latency, and reasoning tokens while avoiding misleading examples and invalid defaults. The piece also covers the production engineering behind enrichment, how Automations and Agent OS agents are exposed as high-level deterministic tools, and why reusable HTTP-based tool definitions let teams run their own MCP runtimes. The core takeaway is that fewer, richer, context-aware tools beat large generic catalogs for real-world agent workflows.
The workbench
Agentlint, platform SDKs, local-first Mac apps, and the occasional weekend experiment. Real code, real trade-offs, work in progress.
Lighthouse for agents. A deterministic website scanner that tells you whether agents can find, understand, and use a site, and proves every conclusion with evidence.
Active · @timbenniks/agentlint
One TypeScript surface for Contentstack (CMA, OAuth, webhooks, image transforms, and generative AI) so you stop stitching four libraries together before you write the actual product.
Active · @timbenniks/contentstack-platform-sdk
The Nuxt module I wish Contentstack shipped: typed composables, live preview, visual builder, personalization, and image optimization in one install.
OSS · nuxt-contentstack on npm
Content types as TypeScript you can import, compile, diff, document, type-generate, and safely promote, so the UI is no longer the source of truth.
OSS · @timbenniks/contentstack-stacksmith
Framework-agnostic tools that expose published Contentstack content to in-tab agents via document.modelContext. Vanilla TypeScript first, React and Next adapters if you want them.
Experimental · @timbenniks/contentstack-webmcp
A hub of agent skills with RBAC, so an agent acting for a user can only reach what that user is allowed to touch, and product managers can propose the next skill without writing it.
Active · Internal + open contributions
The short version
Twenty years building digital platforms for global brands. Now leading Developer Experience at Contentstack, shaping the future of developer-facing products and AI-driven workflows.
Tim Benniks is a Developer Experience and Product leader at Contentstack, where he drives DX, Developer Hub & Marketplace, MCP, and Agent Skills. Tim is a frequent speaker, content creator, ambassador for Cloudinary, Supabase, Nuxt, Algolia and Co-chair of the Enterprise AI Agents Workgroup at the MACH Alliance.
When output is cheap, taste is everything.
AI makes it easier to build. Choosing what deserves to exist still takes judgment, curiosity, and a rested mind.
On camera
Workshops, demos, and conversations from the YouTube channel and Contentstack streams.
Whether you’re new to the concept of AI agents or already exploring ways to scale your content operations, this session will walk through the fundamentals of Agent OS, and how you can get your teams ready ahead of GA.
Learn how to activate Visual Builder, no matter your stack
See how Contentstack Edge allows you to reimagine the possibilities of digital experience by seamlessly integrating intelligent content management with real-time first-party data activation. Experience how brands can…
Stages
ContentCon Amsterdam 2026
ContentCon Amsterdam 2026
MACH X Amsterdam 2026
vuejs.amsterdam 2026
Got a stage, a podcast, or a developer team that needs sharpening? Let's talk.
