AI agents call get_balance to retrieve information from 0g 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 information, which is a read-only operation with no side effects. It does not create, modify, delete, or move funds. Even in a financial context, balance checking is a non-destructive query operation. The low severity reflects that misuse would only expose information already on the public blockchain.
From the tool's definition Tool name 'get_balance' and description 'Get the balance of an address on 0G network' indicate a query operation that retrieves account balance data without modifying state or executing transactions.
Attacks that exploit this kind of access
Get the balance of an address on 0G network. It is categorised as a Read tool in the 0g MCP Server, which means it retrieves data without modifying state.
Register the 0g MCP server in PolicyLayer and add a rule for get_balance: 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 0g. Nothing to install.
get_balance 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_balance 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_balance. 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_balance is provided by the 0g MCP server (opencolin/0g-mcp-server). 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 →