Before sending crypto, check the recipient for address poisoning: lookalikes and bad checksums
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.
Free, offline, read-only: before sending crypto, check whether the recipient address is a lookalike (same first/last hex characters, different middle) of any address you trust, and whether its EIP-55 checksum is valid. Address poisoning stole $76M+ in 12 months by planting such lookalikes in wallet histories.
recipient you are about to pay
addresses you trust (address book, previous real payees)
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http address-poisoning-check https://address-poisoning-check.nextill-pos.workers.dev/mcp
Free, offline, read-only: before sending crypto, check whether the recipient address is a lookalike (same first/last hex characters, different middle) of any address you trust, and whether its EIP-55 checksum is valid. Address poisoning stole $76M+ in 12 months by planting such lookalikes in wallet histories.
| Argument | Type | Description |
|---|---|---|
| to* | string | recipient you are about to pay |
| known | array | addresses you trust (address book, previous real payees) |
{
"type": "object",
"required": [
"to"
],
"properties": {
"to": {
"type": "string",
"pattern": "^0x[0-9a-fA-F]{40}$",
"description": "recipient you are about to pay"
},
"known": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 50,
"description": "addresses you trust (address book, previous real payees)"
}
}
}How to buy the on-chain check (scans the sender's real transfer history on Ethereum/Base/Avalanche for poisoning transfers and lookalikes) via x402 for 0.005 USDC. Does not pay.
No arguments.
{
"type": "object",
"properties": {}
}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 Oct 30, 2026.