AI agents call auditContract to retrieve information from Ethereum Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'audit' prefix suggests static analysis or inspection of smart contract code and security properties. The server explicitly advertises 'contract auditing' alongside read-focused functions like balance checks and transaction analysis. No evidence suggests code execution, contract modification, or fund movement.
From the tool's definition Tool named 'auditContract' with empty description. Based on server context describing 'contract auditing' as a core capability and sibling tools being read-only analysis functions (getEthBalance, getTokenInfo, getTokenPriceHistory, getWalletPnl,…
Documented attack patterns abuse exactly the kind of access auditContract gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ethereum Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for auditContract:
{
"version": "1",
"default": "deny",
"tools": {
"auditContract": {}
}
}auditContract 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.
auditContract. It is categorised as a Read tool in the Ethereum Tools MCP Server, which means it retrieves data without modifying state.
Register the Ethereum Tools MCP server in PolicyLayer and add a rule for auditContract: 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 Ethereum Tools. Nothing to install.
auditContract 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 auditContract 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 auditContract. 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.
auditContract is provided by the Ethereum Tools MCP server (0xgval/evm-mcp-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ethereum Tools, 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.
11 Ethereum Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.