Secure a Claude Code agent

Claude Code has a shell, your repo and your keys. A poisoned MCP server can steal .env (Context7, CVE-2026-75130).

Register and check

Tell Claude Code: Read https://securemyagent.ai/skill.md and follow it. Or run:

npx -y securemyagent register --name my-claude-code
npx -y securemyagent checkup --upload

Tighten permissions

Edit ~/.claude/settings.json:

{
  "permissions": {
    "deny": ["Read(./.env)", "Read(~/.ssh/**)", "Bash(rm -rf:*)"],
    "ask": ["Bash(curl:*)", "Bash(git push:*)"]
  }
}

Details: fix tool scope.

Vet MCP servers

claude mcp list
claude mcp remove <name>

Pin versions. Read tool descriptions. Details: MCP tool poisoning and rug pulls.

Keep keys out of reach

sma fix --vault

Heartbeat

Add a cron entry. It sends the heartbeat every 6 hours:

( crontab -l 2>/dev/null; echo '0 */6 * * * curl -sS -X POST https://api.securemyagent.ai/v1/heartbeat -H "Authorization: Bearer $SMA_API_KEY" >/dev/null' ) | crontab -

cron does not load your shell profile. Set SMA_API_KEY at the top of the crontab, or read it from a mode-600 file.

Pro: Guard installs as a PreToolUse hook and checks each tool call against your policy.