Facio Blog
Payload-powered product notes, security writing, HITL patterns, and operational guidance from the Facio runtime: long sessions, Placet approvals, audit trails, memory, providers, channels, tools, and Docker-first operations.
Showing 186-190 of 281 articles.
Security
A malicious MCP server doesn't need to be called to compromise your agent. Hidden instructions in tool descriptions — invisible to humans, fully visible to LLMs — execute as soon as the schema enters the model context. CVE-2025-6514 infected 437,000 installs. The rug pull is the worst part.
Human-in-the-loop
Human reviewers make mistakes. They rubber-stamp at 3am, they read on their phones and miss context, they apply different standards on different days. Treating HITL as "the human is the final check" creates a single point of failure — and a regulatory one. Here's how to design for the human being imperfect.
Engineering
Brilliant Directories' official MCP server exposes 100 tools covering every resource in the platform — members, posts, leads, reviews, pages, forms, plans — with an OpenAPI 3.1 spec, two install paths, and granular permission gating that lets you turn off destructive operations in the BD Admin.
Product
Most AI agent platforms route customer data through US-hosted infrastructure by default. For European businesses, that's a compliance incident waiting to happen. Facio is built in the EU, for the EU, and the architecture is DSGVO-native from the ground up — data residency, processing boundaries, audit trails, and HITL gating all designed around European data protection requirements. Here's what DSGVO-native actually means and why it matters for production agents.
Engineering
Dodo Payments ships the first MCP plugin I've seen that distributes 8 skills + 2 MCP servers across Claude Code, Codex CLI, Cursor, and OpenCode from a single source — with browser OAuth as the default auth flow.