Etherscan has released a suite of tools that lets AI agents and coding assistants pull live blockchain data directly from the explorer’s API.
The latest release is aimed at developers building agents that need verified onchain facts across more than 60 EVM-compatible networks. The company announced the “Build with AI” launch in a post on X on August 31, 2026.
What Etherscan actually shipped
The release bundles three ways for a machine to reach Etherscan’s data. There is a Model Context Protocol (MCP) server, a hosted interface that agents such as Claude and ChatGPT can call in plain language; a command-line tool for terminals, scripts, and CI pipelines; and a set of installable agent “skills.”
According to Etherscan’s documentation, the MCP server runs at a single endpoint, mcp.etherscan.io/mcp, and exposes 20 tools.
Those cover the basics of reading a chain: native and token balances, normal and internal transactions, transaction and receipt lookups, contract details, gas prices, and event logs. One connection reaches every supported network.
The Command-Line Interface (CLI) follows the API’s structure, with commands in the form etherscan
All of it authenticates with a standard Etherscan API key, and a free key works across every supported chain.
Skills that trace money and read contracts
Etherscan’s public GitHub repository lists four installable skills through a npx skills add command or by copying a folder into an agent’s skills directory.
Etherscan Flow traces money movements across addresses and writes them into a case file. Etherscan Contract Review explains what a verified deployed contract does. A transaction debugger reconstructs what a given transaction did and why. An orchestrator skill routes a task to the right interface.
According to the repository, the stated point of the skills is that “every address, amount, and transaction hash comes from a live API call, never invented.” The whole suite is read-only and respects the API’s normal quotas and rate limits.
Fighting the hallucination problem
Etherscan’s release is seen as a solution to the hallucination problem that also found its way into crypto-AI tools.
Language models can fabricate a wallet balance or a transaction that never happened, both of which can be costly. This usually happens when they do not have the right data, and in most cases, it is because they cannot crawl the pages with the data they are looking for.
In its documentation, Etherscan also warned users not to paste their API keys in fake or fraudulent MCPs posing as legitimate. It stated that only one official MCP server exists and warned that listings on MCP marketplaces calling themselves “Etherscan MCP” are unaffiliated.
Built for an internet where bots outnumber people
So, the scale usage and agentic activities call for appropriate measures to be in place to prevent lapses.
In early June, AI agents surpassed humans as the internet’s largest source of traffic. This was confirmed by Cloudflare CEO Matthew Prince, who said that it happened sooner than he had predicted.
Then Cloudflare Radar data put agentic bots at 57.4% of web traffic against 42.6% for humans, with North America skewed further toward bots at 68.6%.
So far, humans have taken the lead back; however, bots still account for over 35% of the web traffic in the past four weeks.
Even publishers are now working on making it easy for AI agents to access their content.
Etherscan’s release is similar to that move as well. It is publishing machine-readable docs and a query layer built for software readers, not just human ones.
