Get the contract code at a specific address
AI agents call get_code to retrieve information from Monad MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing contract code from the blockchain, which is a non-destructive, non-financial read operation. No side effects occur; it simply queries and returns data. The blast radius of misuse is minimal—an agent could at most enumerate contract code but cannot modify contracts, execute arbitrary functions, or affect blockchain state.
From the tool's definition Tool name 'get_code' and description 'Get the contract code at a specific address' indicate a read-only query operation that retrieves contract bytecode without modifying state.
Attacks that exploit this kind of access
Get the contract code at a specific address. It is categorised as a Read tool in the Monad MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Monad MCP Server MCP server in PolicyLayer and add a rule for get_code: 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 Monad MCP Server. Nothing to install.
get_code 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 get_code 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 get_code. 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.
get_code is provided by the Monad MCP Server MCP server (tairon-ai/monad-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 →