AI agents use import_transactions to create or update resources in Bookie — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bookie environment.
This tool creates or modifies financial records by adding transactions to the accounting system. It is Write (not Destructive) because imports are conceptually reversible through deletion or adjustment. It is not Financial because it does not move actual money or commit external obligations — it only records existing bank/card statements that have already occurred.
From the tool's definition Tool description states 'Import a bank/card statement (CSV) for one account, as balanced double-entry transactions' — this creates new transaction records in the accounting system.
Attacks that exploit this kind of access
Import a bank/card statement (CSV) for one account, as balanced double-entry transactions. Two-step: run with mode=. It is categorised as a Write tool in the Bookie MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bookie MCP server in PolicyLayer and add a rule for import_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.
import_transactions is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the import_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 import_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.
import_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 →