Home / MCP registry index / io.github.ariffazil/arifos
arifOS — Constitutional AI Kernel
io.github.ariffazil/arifos in the official MCP registry.
Endpoint https://mcp.arif-fazil.com/mcp. Source: github.com/ariffazil/arifOS.
The registry describes it as: Constitutional verdict layer for AI agents. SEAL/HOLD before mutation. F1-F13 floors; audit ledger.
We read its 9 tools on 2026-10-27. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
arif_init arif_observe arif_think arif_route arif_memory arif_judge arif_forge arif_seal arif_report
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-ariffazil-arifos)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.