Get the balance of an account
AI agents call account-balance to retrieve information from Ledger 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 account balance information, which is a read-only operation. It queries existing ledger data without creating, modifying, deleting, or executing any transactions. While the data is financial in nature, the tool itself performs no financial operations (no payments, transfers, or commitments).
From the tool's definition Tool name 'account-balance' and description 'Get the balance of an account' indicate a query operation that retrieves financial data without modification or side effects.
Attacks that exploit this kind of access
Get the balance of an account. It is categorised as a Read tool in the Ledger MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Ledger MCP Server MCP server in PolicyLayer and add a rule for account-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 Ledger MCP Server. Nothing to install.
account-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 account-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 account-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.
account-balance is provided by the Ledger MCP Server MCP server (mprokopov/ledger-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 →