AI agents use create_transactions to create or update resources in Ynab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ynab environment.
This tool creates multiple financial transactions in bulk within a budget management system. While it doesn't directly move real money, it writes financial records that affect budget tracking, account balances, and financial reporting. Bulk creation amplifies the blast radius — an AI agent could create many erroneous transactions simultaneously, causing significant data integrity issues across accounts and budgets.
From the tool's definition Create multiple transactions at once. Each transaction needs account_id, date, and amount at minimum.
Attacks that exploit this kind of access
[1 API call, bulk] Create multiple transactions at once. Each transaction needs account_id, date, and amount at minimum. It is categorised as a Write tool in the Ynab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ynab MCP server in PolicyLayer and add a rule for create_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 Ynab. Nothing to install.
create_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 create_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 create_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.
create_transactions is provided by the Ynab MCP server (justmytwospence/ynab-mcp). 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 →