Defi Guard MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 44 installs a week from npm. Last commit 8 Jul 2026.
DeFi safety checks on Base before you sign: honeypot, owner-power scan, approval risk, Aave health.
Today is the operative word: we check Defi Guard MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add defi-guard-mcp -- npx -y @iniit/defi-guard-mcp
{
"mcpServers": {
"defi-guard-mcp": {
"args": [
"-y",
"@iniit/defi-guard-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.defi-guard-mcp]
command = "npx"
args = ["-y", "@iniit/defi-guard-mcp"]
{
"mcpServers": {
"defi-guard-mcp": {
"args": [
"-y",
"@iniit/defi-guard-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"defi-guard-mcp": {
"args": [
"-y",
"@iniit/defi-guard-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
BASE_RPC_URL (Optional Base RPC endpoint; defaults to public fallback pool).
The author declared them in the registry entry; get the values from the project itself.
Read-only crypto safety: token honeypot checks, EIP-712 signature decode, approval scans.
Pre-trade safety check for AI agents: honeypot, tax, liquidity and rug risk before you buy.
Token safety oracle (Base & BSC): honeypot/tax sim, contract powers, A-F risk grade.
Solana pre-trade safety for agents: rug check, honeypot sell-sim, drainer scan, tx preflight.
logi Agent Approval Gate — human approval on the phone before high-risk agent actions.
Pay-per-call x402 checks before an agent moves money: token safety, wallet risk, identifiers.
Pre-trade token safety checks for AI agents on Solana and Base. x402 USDC per call, no key.
Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.
Answers built from our own checks of this server.