Get the token holders for a given token address
AI agents call get_token_holders to retrieve information from Etherscan MCP Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries public blockchain data and returns holder information without creating, modifying, deleting, or executing any operations. It is a straightforward data retrieval operation with no side effects or irreversible consequences. Severity is low because reading blockchain data poses minimal risk even if misused by an AI agent.
From the tool's definition Tool retrieves token holders for a given token address; no state modification occurs. The server description emphasizes 'retrieve' and 'interact with blockchain data' passively.
Attacks that exploit this kind of access
Get the token holders for a given token address. It is categorised as a Read tool in the Etherscan MCP Tool MCP Server, which means it retrieves data without modifying state.
Register the Etherscan MCP Tool MCP server in PolicyLayer and add a rule for get_token_holders: 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 Etherscan MCP Tool. Nothing to install.
get_token_holders 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_token_holders 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_token_holders. 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_token_holders is provided by the Etherscan MCP Tool MCP server (septemhill/etherscan-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 →