feed_item_spending_category_update

WHAT IT DOES

What feed_item_spending_category_update does on Starling Bank

AI agents use feed_item_spending_category_update to create or update resources in Starling Bank — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Starling Bank environment.

WHY IT NEEDS A POLICY

Why feed_item_spending_category_update needs a policy

This tool modifies transaction metadata (spending category) reversibly within a financial account. While it does not move money directly (which would be Financial), it operates on financial account data and could affect reporting, budgeting, or account organization if misused by an AI agent.

From the tool's definition Tool name and description indicate it 'Update[s] the spending category for a transaction' — a modification operation on financial transaction data within a Starling Bank account.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

feed_item_spending_category_update Rate-limited

feed_item_spending_category_update stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "feed_item_spending_category_update": {
      "limits": [
        {
          "counter": "feed_item_spending_category_update_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Starling Bank, so you can run agents against it safely.

FAQ

Questions about feed_item_spending_category_update

What does the feed_item_spending_category_update tool do? +

Update the spending category for a transaction. It is categorised as a Write tool in the Starling Bank MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on feed_item_spending_category_update? +

Register the Starling Bank MCP server in PolicyLayer and add a rule for feed_item_spending_category_update: 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 Starling Bank. Nothing to install.

What risk level is feed_item_spending_category_update? +

feed_item_spending_category_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit feed_item_spending_category_update? +

Yes. Add a rate_limit block to the feed_item_spending_category_update 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.

How do I block feed_item_spending_category_update completely? +

Set action: deny in the PolicyLayer policy for feed_item_spending_category_update. 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.

What MCP server provides feed_item_spending_category_update? +

feed_item_spending_category_update is provided by the Starling Bank MCP server (starling-bank-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.