Update the user note for a transaction
AI agents use feed_item_note_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.
This tool modifies transaction notes, which are user-facing metadata attached to financial transactions. While the change is reversible (notes can be updated again), it affects financial transaction records in a banking context. The severity is medium rather than high because updating notes does not move funds, change account settings, or cause financial loss—it only modifies annotation/metadata.
From the tool's definition Tool name 'feed_item_note_update' and description 'Update the user note for a transaction' indicate modification of existing transaction metadata.
Attacks that exploit this kind of access
Update the user note 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.
Register the Starling Bank MCP server in PolicyLayer and add a rule for feed_item_note_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.
feed_item_note_update 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 feed_item_note_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.
Set action: deny in the PolicyLayer policy for feed_item_note_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.
feed_item_note_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.
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 →