AI agents use merge_category 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 or modifies data reversibly (Write category) rather than being Destructive, as the source category merge is a reorganization operation, not an irreversible deletion. It is not Financial because it does not move money between accounts or commit financial obligations—it only reorganizes categorical metadata and historical budget allocations.
From the tool's definition The tool 'merge_category' modifies existing data by re-categorizing transactions and moving budgeted amounts.
Attacks that exploit this kind of access
[Variable API calls] [Workflow] Merges a source category into a target category: re-categorizes all transactions and moves all historical budgeted amounts. 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 merge_category: 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.
merge_category 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 merge_category 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 merge_category. 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.
merge_category 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 →