Get the contract class definition in the given block associated with the given hash
AI agents call starknet_getClass to retrieve information from Starknet MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries contract class definitions from the Starknet blockchain, which is a read-only state retrieval operation. It retrieves public blockchain data without side effects, transaction execution, or financial implications. The blast radius of misuse is minimal—an agent could query information it shouldn't see, but cannot alter chain state or move assets. Categorized as Read with low severity.
From the tool's definition Tool name 'starknet_getClass' with description 'Get the contract class definition in the given block associated with the given hash' performs a retrieval operation on blockchain state without modifying data.
Documented attack patterns abuse exactly the kind of access starknet_getClass gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Starknet MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for starknet_getClass:
{
"version": "1",
"default": "deny",
"tools": {
"starknet_getClass": {}
}
} starknet_getClass 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.
Get the contract class definition in the given block associated with the given hash. It is categorised as a Read tool in the Starknet MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Starknet MCP Server MCP server in PolicyLayer and add a rule for starknet_getClass: 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 Starknet MCP Server. Nothing to install.
starknet_getClass 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 starknet_getClass 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 starknet_getClass. 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.
starknet_getClass is provided by the Starknet MCP Server MCP server (milancermak/starknet-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Starknet MCP Server, 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.
21 Starknet MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.