gnanagurusrgs

It's an MCP server, so it works from Claude Code, Cursor, Windsurf, Zed instead of being tied to one of them.

sandbox-profiles is a solid primitive for local agents. The missing piece in production is the tool layer — even a sandboxed agent can still make dangerous API calls if the MCP tools it has access to aren't individually authed and scoped.

The real stack is: sandbox the runtime (what Agent Safehouse does) + scope the tools (what we do with JIT OAuth at the MCP layer). Neither alone is enough.

Nice work shipping this.

Growing up as an integration engineer, I built my career religiously reading the Enterprise Integration Patterns book from Gregor Hohpe. Content-Based Router, Dead Letter Channel, Claim Check these weren't just patterns, they were how I thought about systems. That book shaped an entire generation of us who built middleware, ESBs, and messaging infrastructure.

Two decades later, I found myself staring at a eerily familiar set of problems but with a completely different consumer. Not applications. Not services. AI agents.

It's been an exciting and one-of-its-kind experience working with the Arcade tool engineering team to extract implementation patterns from 7,000+ production tools. Especially Evan Tahler Renato Byrro & Francisco Liberal

54 patterns across 10 categories, so everyone building tools and MCP servers can ship higher quality tools for their agents.

A couple things that make this practical:

Every pattern downloads as a flash card. Drop them into your architecture decks, design reviews, team workshops.

Every pattern exports as markdown / llms.txt for your IDE.

The workflow: point your coding agent at one or more patterns and say "build an MCP server for this API."

The pattern becomes your implementation spec.