ERC-20 token transfer history for an Ethereum address (via Etherscan V2). Each transfer: hash, block, timestamp, from/to, token contract, name, symbol, decimals, and value (raw + decimal-adjusted). Optionally filter to one token contract. Paginate with page + offset. Defaults to Ethereum mainnet;...
AI agents call crypto.token-transfers to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs historical data retrieval only—it queries blockchain transaction records via Etherscan V2 API to show past token transfers to/from a wallet. While it operates in a financial domain (crypto tokens), it does not move money, execute trades, or commit financial obligations; it merely reads existing transaction history.
From the tool's definition The tool retrieves and queries ERC-20 token transfer history for an Ethereum address. Key verbs: 'retrieves', 'trace what tokens', with pagination parameters (page, offset) for data retrieval.
Attacks that exploit this kind of access
ERC-20 token transfer history for an Ethereum address (via Etherscan V2). Each transfer: hash, block, timestamp, from/to, token contract, name, symbol, decimals, and value (raw + decimal-adjusted). Optionally filter to one token contract. Paginate with page + offset. Defaults to Ethereum mainnet; other EVM chains by chainId where upstream coverage allows. Trace what tokens a wallet sent/received. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for crypto.token-transfers: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
crypto.token-transfers is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crypto.token-transfers rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for crypto.token-transfers. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
crypto.token-transfers is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →