AI agents call audit_account_reconciliation 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.
Auditing an account involves retrieving and reviewing account information to verify reconciliation status. This is a read operation that gathers data for inspection purposes. While the YNAB server as a whole includes destructive and financial tools, this specific tool's name and description indicate it only retrieves data for review. No evidence suggests it modifies, deletes, or moves funds.
From the tool's definition Tool name contains 'audit' and description states 'Audit an account', which is a read-only review operation.
Attacks that exploit this kind of access
[2-4 API calls] [Workflow] Audit an account. 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 audit_account_reconciliation: 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.
audit_account_reconciliation 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 audit_account_reconciliation 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 audit_account_reconciliation. 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.
audit_account_reconciliation 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 →