Token safety check for AI agents on 45 chains: honeypot, tax, owner powers, LP lock, holders.
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.
Check whether a crypto token is safe to buy, hold or sell before trading it. Works on 45 chains: Ethereum, BNB Chain, Base, Arbitrum, Polygon, Optimism, Avalanche and other EVM chains, plus Solana, Tron and Sui. Detects honeypots (live sell simulation on Ethereum, BNB Chain, Base), buy/sell tax, owner powers (mint, pause, blacklist, change tax, hidden owner), Solana mint/freeze authority and Token-2022 traps, proxy/upgradeable contracts, LP lock, top-holder concentration, source verification and age. Returns verdict SAFE, CAUTION or DANGER, a 0-100 score, and plain-English reasons citing GoPlus, honeypot.is, RugCheck or on-chain RPC. Free: 3 checks per day per IP; when used up, the result explains the paid x402 endpoint instead. Not financial advice.
Token contract address: 0x… (EVM), base58 mint (Solana), T… (Tron) or coin type 0x…::module::NAME (Sui).
Chain key from list_chains (aliases and EVM chain ids like '1' or '8453' also work). Defaults to bsc for 0x addresses; Solana, Tron and Sui addresses are auto-detected if omitted.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http agent-token-check https://agent-token-check.pages.dev/mcp
Check whether a crypto token is safe to buy, hold or sell before trading it. Works on 45 chains: Ethereum, BNB Chain, Base, Arbitrum, Polygon, Optimism, Avalanche and other EVM chains, plus Solana, Tron and Sui. Detects honeypots (live sell simulation on Ethereum, BNB Chain, Base), buy/sell tax, owner powers (mint, pause, blacklist, change tax, hidden owner), Solana mint/freeze authority and Token-2022 traps, proxy/upgradeable contracts, LP lock, top-holder concentration, source verification and age. Returns verdict SAFE, CAUTION or DANGER, a 0-100 score, and plain-English reasons citing GoPlus, honeypot.is, RugCheck or on-chain RPC. Free: 3 checks per day per IP; when used up, the result explains the paid x402 endpoint instead. Not financial advice.
| Argument | Type | Description |
|---|---|---|
| chain | string | Chain key from list_chains (aliases and EVM chain ids like '1' or '8453' also work). Defaults to bsc for 0x addresses; Solana, Tron and Sui addresses are auto-detected if omitted. |
| token* | string | Token contract address: 0x… (EVM), base58 mint (Solana), T… (Tron) or coin type 0x…::module::NAME (Sui). |
{
"type": "object",
"required": [
"token"
],
"properties": {
"chain": {
"enum": [
"bsc",
"eth",
"base",
"arbitrum",
"polygon",
"optimism",
"avalanche",
"solana",
"tron",
"sui",
"opbnb",
"linea",
"zksync",
"blast",
"scroll",
"mantle",
"unichain",
"sonic",
"berachain",
"gnosis",
"cronos",
"worldchain",
"soneium",
"abstract",
"monad",
"xlayer",
"manta",
"story",
"hashkey",
"morph",
"merlin",
"bitlayer",
"zircuit",
"plasma",
"conflux",
"kcc",
"robinhood",
"stable",
"pharos",
"gravity",
"mint",
"zklink",
"zkfair",
"fon",
"jovay"
],
"type": "string",
"default": "bsc",
"description": "Chain key from list_chains (aliases and EVM chain ids like '1' or '8453' also work). Defaults to bsc for 0x addresses; Solana, Tron and Sui addresses are auto-detected if omitted."
},
"token": {
"type": "string",
"description": "Token contract address: 0x… (EVM), base58 mint (Solana), T… (Tron) or coin type 0x…::module::NAME (Sui)."
}
},
"additionalProperties": false
}List the blockchains check_token supports, with the chain key to pass, chain id, whether a live honeypot sell simulation is available, and which data sources are used. Free, no quota.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}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.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.