AI agents call list_category_transactions to retrieve information from Ynab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries financial transaction data for a given category without creating, modifying, deleting, or moving money. While it operates in a financial domain (YNAB budget management), the action itself is read-only with no side effects. The blast radius of misuse is low—an agent retrieving transaction data cannot cause financial harm, data loss, or unwanted state changes.
From the tool's definition Tool name 'list_category_transactions' and description 'List transactions for a specific category' indicate retrieval of transaction data with no modification or deletion.
Attacks that exploit this kind of access
[1 API call] List transactions for a specific category. It is categorised as a Read tool in the Ynab MCP Server, which means it retrieves data without modifying state.
Register the Ynab MCP server in PolicyLayer and add a rule for list_category_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.
list_category_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 list_category_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 list_category_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.
list_category_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 →