Is @iniit/defi-guard-mcp safe?
Safety layer that checks a DeFi token or transaction on Base before you sign: honeypot detection, owner-power (mint/pause/blacklist) bytecode scan, unlimited-approval risk, Aave V3 position health, and gas-aware DEX quotes.
If an AI agent using this server were tricked, the damage it could do through this server is limited.
Why: no high-reach capabilities found.
What it can do
No commands, file changes, browser control or database access found in its code.
Tools it offers your AI (6):
- aave_position_health
- quote_swap
- token_risk_snapshot
- token_safety_screen
- scan_dangerous_capabilities
- approval_risk
Code patterns worth reviewing
No risky code patterns matched in the files we read (1).
Install it pinned
{
"mcpServers": {
"defi-guard": {
"command": "npx",
"args": ["-y", "@iniit/defi-guard-mcp@0.2.0"]
}
}
}Check your whole MCP setup
Agent Verify checks the servers in your Claude, Cursor and VS Code config — including whole-drive access and keys stored in plain text.
Maintain @iniit/defi-guard-mcp?
Show users you've thought about access: add the badge below. If something here is wrong or you've released a fix, ask for a re-scan — we update pages on request.
[](https://aimodularity.com/agentverify/mcp/iniit-defi-guard-mcp/)
Agent Verify reads the package published on npm as text — it is never installed or run. Ratings describe capability, not intent, and are an automated, evidence-based check, not a guarantee. Scanner 2.0.0.