Run a report and render it as markdown or CSV. Accepts the same parameters as generate_report plus a format. Markdown is human-readable; CSV is suitable for spreadsheet import. The report data is fetched fresh — no need to call generate_report first.
AI agents call export_report 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.
export_report only reads and formats data (account balances, transactions, etc.) into markdown or CSV output. It has no side effects, does not move money, and does not modify or delete any records. It is functionally equivalent to generate_report with an added output format parameter. Severity is low because misuse only exposes financial report data.
From the tool's definition 'Run a report and render it as markdown or CSV' and 'The report data is fetched fresh — no need to call generate_report first' — the tool retrieves and formats existing financial data without modifying or deleting anything.
Attacks that exploit this kind of access
Run a report and render it as markdown or CSV. Accepts the same parameters as generate_report plus a format. Markdown is human-readable; CSV is suitable for spreadsheet import. The report data is fetched fresh — no need to call generate_report 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 export_report: 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.
export_report 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 export_report 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 export_report. 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.
export_report 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 →