Returns the event logs from an address, filtered by topics and block range.
AI agents call logs__getLogsByAddressAndTopics to retrieve information from Etherscan MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical event logs from the Ethereum blockchain filtered by address and topics. It performs no side effects, creates no transactions, executes no code, and modifies no state. Even though it accesses financial blockchain data, the tool itself only reads and returns information. The risk is low because querying logs cannot cause harm regardless of how an AI uses the query parameters.
From the tool's definition Tool description states it 'Returns the event logs from an address' — a retrieval operation. The Etherscan API context confirms this is a query-only function that reads blockchain data without modification or execution of operations.
Documented attack patterns abuse exactly the kind of access logs__getLogsByAddressAndTopics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Etherscan MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for logs__getLogsByAddressAndTopics:
{
"version": "1",
"default": "deny",
"tools": {
"logs__getLogsByAddressAndTopics": {}
}
}logs__getLogsByAddressAndTopics is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Returns the event logs from an address, filtered by topics and block range. It is categorised as a Read tool in the Etherscan MCP MCP Server, which means it retrieves data without modifying state.
Register the Etherscan MCP server in PolicyLayer and add a rule for logs__getLogsByAddressAndTopics: 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 Etherscan MCP. Nothing to install.
logs__getLogsByAddressAndTopics 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 logs__getLogsByAddressAndTopics 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 logs__getLogsByAddressAndTopics. 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.
logs__getLogsByAddressAndTopics is provided by the Etherscan MCP server (xiaok/etherscan-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Etherscan MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
56 Etherscan MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.