Get details of a specific feed item (transaction) including any attachments
AI agents call feed_item_get to retrieve information from Starling Bank without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves transaction details and attachments from a financial account, which is a read-only operation with no ability to modify, delete, or execute financial transactions. While it accesses sensitive financial information (transactions), it does not create, modify, delete, or transfer funds.
From the tool's definition Tool name 'feed_item_get' and description 'Get details of a specific feed item (transaction) including any attachments' indicate retrieval of transaction data without modification or side effects.
Attacks that exploit this kind of access
Get details of a specific feed item (transaction) including any attachments. It is categorised as a Read tool in the Starling Bank MCP Server, which means it retrieves data without modifying state.
Register the Starling Bank MCP server in PolicyLayer and add a rule for feed_item_get: 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_get 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 feed_item_get 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_get. 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_get 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 →