Returns the balance of the account of given address
AI agents call eth_getBalance to retrieve information from EVM 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 blockchain account balance data without creating, modifying, deleting, or executing any operations. It is a read-only query that returns information about an existing state. The blast radius of misuse is minimal—an attacker could only gather information about account balances, which is already public blockchain data. No financial transactions, code execution, or state changes are possible.
From the tool's definition Tool name is 'eth_getBalance' and description states it 'Returns the balance of the account of given address' — a pure query operation with no side effects or state modification.
Attacks that exploit this kind of access
Returns the balance of the account of given address. It is categorised as a Read tool in the EVM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the EVM MCP Server MCP server in PolicyLayer and add a rule for eth_getBalance: 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 EVM MCP Server. Nothing to install.
eth_getBalance 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 eth_getBalance 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 eth_getBalance. 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.
eth_getBalance is provided by the EVM MCP Server MCP server (jamesanz/evm-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 →