AI agents call get_balances to retrieve information from Crypto Multi-MCP Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves financial data (balances) but does not modify, transfer, or spend funds. It has no side effects beyond returning information. While balance data could be sensitive, the action itself is read-only and presents minimal risk if invoked by an AI agent. Classification as Read is appropriate; severity is low because data disclosure alone causes no direct harm compared to execute or financial operations.
From the tool's definition Tool name 'get_balances' indicates retrieval of balance information. No description provided, but naming convention and context (sibling tools like 'erc20_balance', 'eth_balance') suggest a read-only query operation that retrieves wallet/account balances…
Documented attack patterns abuse exactly the kind of access get_balances gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crypto Multi-MCP Hub, and nothing reaches the server without passing your rules. This is the rule we recommend for get_balances:
{
"version": "1",
"default": "deny",
"tools": {
"get_balances": {}
}
}get_balances 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_balances. It is categorised as a Read tool in the Crypto Multi-MCP Hub MCP Server, which means it retrieves data without modifying state.
Register the Crypto Multi-MCP Hub MCP server in PolicyLayer and add a rule for get_balances: 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 Crypto Multi-MCP Hub. Nothing to install.
get_balances 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_balances 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_balances. 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_balances is provided by the Crypto Multi-MCP Hub MCP server (pellenybe/crypto-mcp-server---by-corax-colab). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crypto Multi-MCP Hub, 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.
48 Crypto Multi-MCP Hub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.