Armour – A secure stdio MCP proxy, written in Go
At my last company, we connected Claude Code and Cursor to almost all our internal services via MCP. It made the team incredibly fast, but we hit a wall: permissions. If you give an agent "Read Only" access, it can’t actually fix anything. If you give it "Write" access, it’s only a matter of time before a hallucination or a bad prompt results in a deleted database or a nuked production bucket. We had a few "close calls" that convinced us that simply reducing IAM permissions makes agents useless. I built Armour (https://github.com/fuushyn/armour) to solve this. It’s a…
Armour – A secure stdio MCP proxy, written in Go launched on January 20, 2026 with 23 votes, #690 of 14,584 launches that month and more than 90% of that year's launches.
In plain words
Armour is a secure proxy for Model Context Protocol (MCP) servers written in Go that sits between AI coding tools and internal services. It addresses the permission problem where agents either lack write access to be useful or have full access to cause damage through hallucinations. The proxy acts as middleware that manages tool access, allowing teams to maintain security by default while preserving agent capabilities. It's designed for developers and teams running AI agents like Claude Code and Cursor against internal infrastructure.
written from the facts on this page · September 2026
From the sources
Firewall for AI agents. Contribute to fuushyn/armour development by creating an account on GitHub.
In the maker’s words, at launch
At my last company, we connected Claude Code and Cursor to almost all our internal services via MCP. It made the team incredibly fast, but we hit a wall: permissions. If you give an agent "Read Only" access, it can’t actually fix anything. If you give it "Write" access, it’s only a matter of time before a…
Does a similar job
all alternatives →
KastraJul 2026 · kastra.ai · ▲332Hi HN, Fernando and I built Kastra. Kastra intercepts AI agent tool calls and evaluates them against deterministic policies before they execute. We built this product to control pre- and post-inference workloads. This is aimed at developers using coding agents like Claude Code, Codex, Cursor, and OpenClaw. Kastra pushes an allow, hold, and deny decision before the action runs. You can build these policies in plain English from the web app. The interception engine evaluates the tools, targets, and parameters of every action at sub 1ms at a scale of billions of interceptions per day. We also…
Agent-of-empires: OpenCode and Claude Code session managerJan 2026 · github.com · ▲118Hi! I’m Nathan: an ML Engineer at Mozilla.ai: I built agent-of-empires (aoe): a CLI application to help you manage all of your running Claude Code/Opencode sessions and know when they are waiting for you. - Written in rust and relies on tmux for security and reliability - Monitors state of cli sessions to tell you when an agent is running vs idle vs waiting for your input - Manage sessions by naming them, grouping them, configuring profiles for various settings I'm passionate about getting self-hosted open-weight LLMs to be valid options to compete with proprietary closed models. One…
Salestrics MCPAug 2026 · salestrics.com · ▲37Hey HN, I’m Austin, founder of Salestrics (salestrics.com). The Problem: > Most AI agents today are trapped in chat windows. While models are smart enough to run complex multi-step workflows, giving them production access to business context (CRM, support, billing) usually means managing unsafe local API keys or hacking together fragile point-solution scripts. What We Built: We built Salestrics to serve as both an all-in-one revenue workspace (CRM, service desk, billing, docs, email) and a production-grade Model Context Protocol (MCP) execution proxy. How It Works: Unified Context: Instead…
Self-hosted company OS, Claude Code and Codex agents in departmentsSep 2026 · github.com · ▲50Hi HN, i am Dimitris, I have been using Claude Code and Codex agents, for some time now from the beggining i had been using them from inside my terminal mainly for coding. For the past 3 years i kept building so i have a homelab and a business server, which already has a lot of vms, so a lot of things to manage. So i decided to start building my own ideal version of using claude code, and codex flexibly and connect them easily with all my vms and infra but at the same time keep using them for coding, and as a personal assistant for daily use. So for the past months I built OtoDock. Its a…
I built a smart proxy so your coding agent can run looseJul 2026 · trollbridge.dev · ▲14The only way to go fast is full YOLO mode in your coding agent. I've got the local sandbox figured out (pro tip: Incus VMs work great) but I wanted to keep my agents from doing things like inadvertently blowing up my cloud services or chasing a prompt to POST to some random website. I struggle most with this on my side projects where my permission model isn't quite as robust as it is at the office. I started with a firewall on the Incus container but every time the agent needed access to something new, I was poking more holes in it - and it didn't differentiate between HTTP verbs. I've been…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
