"author:toxicwind" matching MCP servers:

Enables agents to retrieve their current identity from IDENTITY.md and route durable lessons, preferences, rules, and corrections to the appropriate standing file over MCP stdio.

Enables background agents to control Hyprland windows, input, screenshots, and session actions while racing actuation paths and refusing stale or unverified focus targets.

Enables AI agents to run ProjectDiscovery reconnaissance tools — subdomain discovery, DNS resolution, HTTP probing, port scanning, crawling, template scanning, and chained bounty workflows — through MCP under alternate tool names, so the underlying binary names never appear in the tool catalog. Includes confirm gates for intrusive scans and no-shell argument-array spawning.

Enables secure file listing, pulling, dry-run previews, and gated pushing between a local sandbox and a remote /home/toxic tree over SSH, with path confinement and destructive-operation confirmations.