AI agents call query_transactions to retrieve information from Bookie without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves financial transaction data based on filters but does not create, modify, delete, or move money. It is a read-only operation that returns existing journal entries. While the data domain is financial (personal and business finances), the tool itself does not commit financial obligations or move funds—it only displays them. Therefore, it falls under Read rather than Financial.
From the tool's definition Tool name is 'query_transactions' and description states it 'List journal entries with their postings, filtered by date range and/or account.
Attacks that exploit this kind of access
List journal entries with their postings, filtered by date range and/or account. Returns newest first. It is categorised as a Read tool in the Bookie MCP Server, which means it retrieves data without modifying state.
Register the Bookie MCP server in PolicyLayer and add a rule for query_transactions: 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 Bookie. Nothing to install.
query_transactions 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 query_transactions 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 query_transactions. 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.
query_transactions is provided by the Bookie MCP server (yuens1002/bookie). 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 →