Pay-per-call rug-pull, honeypot and token safety checks for any ERC-20 on Base (x402, USDC).
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Deep Base token safety / rug-pull / honeypot check: everything in token_safety_check plus DEX liquidity (Uniswap, Aerodrome), holder shares, mint/blacklist/fee functions, a simulated buy, and a 0-100 risk score with a low/medium/high verdict. Price: $0.02 USDC on Base via x402.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http base-token-safety https://a1.project-swarm.xyz/mcp
Deep Base token safety / rug-pull / honeypot check: everything in token_safety_check plus DEX liquidity (Uniswap, Aerodrome), holder shares, mint/blacklist/fee functions, a simulated buy, and a 0-100 risk score with a low/medium/high verdict. Price: $0.02 USDC on Base via x402.
| Argument |
|---|
| Type |
|---|
| Description |
|---|
| address* | string |
{
"type": "object",
"title": "token_deep_safety_checkArguments",
"required": [
"address"
],
"properties": {
"address": {
"type": "string",
"title": "Address"
}
}
}Base token safety check before you swap or accept a token: ERC-20 metadata, supply, upgradeable proxy, owner / renounced, paused, and risk flags. Read-only, about 1 second. Price: $0.005 USDC on Base via x402.
| Argument | Type | Description |
|---|---|---|
| address* | string |
{
"type": "object",
"title": "token_safety_checkArguments",
"required": [
"address"
],
"properties": {
"address": {
"type": "string",
"title": "Address"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 15, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.