Best Guard AI Skills & MCP Servers
30 curated Guard skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Agent Harness Sdk
Primitives for building agent harnesses: tools, guards, checks, hooks, observability.
Gitlab Cli
MCP server for GitLab with tools for repositories, issues, merge requests, pipelines, releases, and guarded write operations.
Blackwall
BLACK_WALL MCP server — a pre-action risk check your AI agent calls before any irreversible action (send email, move money, run SQL, delete data).
Unerr
Your AI agent has read your codebase but still can't safely change it. unerr is a local guardrail that hands the agent the call graph and your rules at the moment it edits.
Server
MCP server for DashClaw governance — guard, record, invoke, and discover capabilities.
Zarq
Evaluate crypto token safety with real-time trust scores and structural risk signals. Identify potential market distress and impending collapses to safeguard your digital investments. Compare assets head-to-head using multi-dimensional security and compliance metrics.
About Guard skills on iClaude
iClaude is the universal install layer for AI skills. Every Guard skill on this page can be installed into Claude Code, Claude Desktop, Cursor, ChatGPT, n8n, Codex, and more — using a single copy-paste command. No config drift, no per-stack adapters, no manual MCP wiring.