$ loading_
Provides exactly-once guards for AI agents to prevent duplicate actions on retries.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.azender1/safeagent" MCP server from askskill: Run: claude mcp add 'io-github-azender1-safeagent' -- npx -y safeagent-exec-guard
Add offline, deterministic pre-action safety gates with signed verdicts for AI agents.
Add pay-per-call security guards and trust checks to AI agents.
Gate blockchain actions from AI agents with explainable allow, warn, or block decisions.
Add DeFi wallet safety, token risk checks, and transaction simulation for AI agents.
Set AI agent budgets, enforce spend limits, and audit every decision.
Add a universal kill switch and spend guard for spending AI agents.