Any Ethereum or Base transaction in plain words, with red flags. Paid per call via x402.
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.
Plain-words explanation of one Ethereum or Base transaction: a one-line summary (swap, send, approval, bridge, deposit, NFT transfer, failed call), every token and NFT movement with symbols, the account's net change, approvals (incl. Permit2), protocols touched, and red flags: unlimited or wallet approvals, look-alike tokens, address-poisoning spam, failed calls. Handles smart-account (ERC-4337) and gasless USDC (EIP-3009 / x402) transactions. Costs $0.01 (x402, USDC).
Transaction hash, 0x followed by 64 hex characters
Chain: ethereum, base
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 transaction-explainer https://tx.changefeed.dev/mcp
Plain-words explanation of one Ethereum or Base transaction: a one-line summary (swap, send, approval, bridge, deposit, NFT transfer, failed call), every token and NFT movement with symbols, the account's net change, approvals (incl. Permit2), protocols touched, and red flags: unlimited or wallet approvals, look-alike tokens, address-poisoning spam, failed calls. Handles smart-account (ERC-4337) and gasless USDC (EIP-3009 / x402) transactions. Costs $0.01 (x402, USDC).
| Argument | Type | Description |
|---|---|---|
| hash* | string | Transaction hash, 0x followed by 64 hex characters |
| chain* | string | Chain: ethereum, base |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"chain",
"hash"
],
"properties": {
"hash": {
"type": "string",
"description": "Transaction hash, 0x followed by 64 hex characters"
},
"chain": {
"type": "string",
"description": "Chain: ethereum, base"
}
}
}Free: status (success, failed, pending), block, confirmations, fee, what kind of transaction it is, and how many red flags it has, without the details. About 20 calls a minute per client.
| Argument | Type | Description |
|---|---|---|
| hash* | string | Transaction hash, 0x followed by 64 hex characters |
| chain* | string | Chain: ethereum, base |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"chain",
"hash"
],
"properties": {
"hash": {
"type": "string",
"description": "Transaction hash, 0x followed by 64 hex characters"
},
"chain": {
"type": "string",
"description": "Chain: ethereum, base"
}
}
}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 17, 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.