Retrieve year-to-date (YTD) and 1-year returns for a specific fund.
AI agents call get_returns to retrieve information from Northern Trust MCP Layer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical financial performance metrics (fund returns) without creating, modifying, deleting, or executing any operations. It has no side effects and presents minimal risk if misused by an AI agent—the worst outcome would be unauthorized access to financial data already publicly available or intended for authorized users.
From the tool's definition Tool name is 'get_returns' and description states 'Retrieve year-to-date (YTD) and 1-year returns for a specific fund.' The verb 'Retrieve' and lack of any modification, deletion, or execution language clearly indicate a read-only data retrieval operation.
Attacks that exploit this kind of access
Retrieve year-to-date (YTD) and 1-year returns for a specific fund. It is categorised as a Read tool in the Northern Trust MCP Layer MCP Server, which means it retrieves data without modifying state.
Register the Northern Trust MCP Layer MCP server in PolicyLayer and add a rule for get_returns: 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 Northern Trust MCP Layer. Nothing to install.
get_returns 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 get_returns 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 get_returns. 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.
get_returns is provided by the Northern Trust MCP Layer MCP server (vbzvibin/mcp_v3). 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 →