Transaction history for an Ethereum address (via Etherscan V2). Returns normal transactions newest-first: hash, block, timestamp, from/to, value (wei + ETH), gas used, gas price, decoded method id + function name, error flag, and any contract created. Paginate with page + offset; bound with start...
AI agents call crypto.address-history 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 purely retrieves and queries historical blockchain transaction data from a public explorer API. It has no side effects on blockchain state, accounts, or funds. The only parameters are read-only filters (page, offset, startBlock, endBlock, chainId).
From the tool's definition Tool description explicitly states it 'Returns' transaction history and retrieves data 'via Etherscan V2' with pagination parameters. No mutation, deletion, or execution capabilities mentioned.
Attacks that exploit this kind of access
Transaction history for an Ethereum address (via Etherscan V2). Returns normal transactions newest-first: hash, block, timestamp, from/to, value (wei + ETH), gas used, gas price, decoded method id + function name, error flag, and any contract created. Paginate with page + offset; bound with startBlock/endBlock. Defaults to Ethereum mainnet; other EVM chains by chainId where upstream coverage allows. Net-new vs crypto.tx (single-hash receipt). 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.address-history: 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.address-history 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.address-history 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.address-history. 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.address-history 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 →