Mycrab Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mycrab Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server for mycrab.space — instant public HTTPS URLs via Cloudflare Tunnels for AI agents.
<!-- mcp-name: io.github.isgudtek/mycrab-mcp -->
uvx mycrab-mcpAdd to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"mycrab": {
"command": "uvx",
"args": ["mycrab-mcp"]
}
}
}| Tool | Description |
|---|---|
check_domain | Check if a subdomain is available on mycrab.space |
setup_free_tunnel | Get the command for a free tunnel (auto subdomain, expires 61 min) |
buy_domain_sol | Reserve a permanent subdomain after paying 0.05 SOL on Solana mainnet |
get_skill_docs | Fetch the full SKILL.md — all templates, commands, and advanced usage |
After install, agents have native mycrab tools in every session:
# Check availability
check_domain("mybot")
# Free throwaway tunnel — live in <60 seconds
setup_free_tunnel()
# → "curl -s https://mycrab.space/agent-setup-auto.sh | bash"
# Permanent custom subdomain (autonomous x402 flow)
buy_domain_sol("mybot", "<solana_tx_signature>")
# → {"setup_token": "...", "setup_command": "..."}~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.