getCode

Get the deployed bytecode at an address. Returns empty if the address is an EOA (not a contract). If chainId is omitted, queries all supported chains.

SERVERAgentek Eth SOURCEnanidao/agentek

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/nanidao-agentek/getcode.md

WHAT IT DOES

What getCode does on Agentek Eth

AI agents call getCode to retrieve information from Agentek Eth without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why getCode is rated Low

This is a Read operation—it retrieves blockchain bytecode at a given address with no side effects or state modifications. It merely returns existing data. Severity is medium rather than low because bytecode inspection could facilitate reconnaissance for attacking contracts (enabling subsequent exploit attempts), which represents moderate risk if an AI agent systematically probes contract security for malicious…

From the tool's definition Tool description states 'Get the deployed bytecode at an address' and 'Returns empty if the address is an EOA'. This is a pure read operation that retrieves bytecode data without modifying state. The tool queries blockchain data.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs getCode safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Agentek Eth, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For getCode, this is the rule to start with:

getCode Allowed

getCode is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "getCode": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Agentek Eth, apply this rule, and every getCode call is checked against it from then on.

FAQ

Questions about getCode

What does the getCode tool do? +

Get the deployed bytecode at an address. Returns empty if the address is an EOA (not a contract). If chainId is omitted, queries all supported chains. It is categorised as a Read tool in the Agentek Eth MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on getCode? +

Register the Agentek Eth MCP server in PolicyLayer and add a rule for getCode: 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 Agentek Eth. Nothing to install.

What risk level is getCode? +

getCode is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit getCode? +

Yes. Add a rate_limit block to the getCode 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.

How do I block getCode completely? +

Set action: deny in the PolicyLayer policy for getCode. 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.

What MCP server provides getCode? +

getCode is provided by the Agentek Eth MCP server (nanidao/agentek). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Agentek Eth, and thousands of servers like it.

This server

All 193 Agentek Eth tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →