Get a detailed breakdown of the assets held within ETFs and mutual funds using the FMP ETF & Fund Holdings API. Access real-time data on the specific securities and their weights in the portfolio, providing insights into asset composition and fund strategies.
AI agents call getFundHoldings to retrieve information from Financial Modeling Prep MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool exclusively queries and retrieves financial data about fund holdings without any side effects. It neither modifies data, executes code, deletes information, nor initiates financial transactions. The operation is idempotent and informational in nature, making it a straightforward Read operation with low risk even if misused by an AI agent.
From the tool's definition Tool provides retrieval of 'detailed breakdown of the assets held within ETFs and mutual funds' and 'real-time data on the specific securities and their weights' with no indication of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Get a detailed breakdown of the assets held within ETFs and mutual funds using the FMP ETF & Fund Holdings API. Access real-time data on the specific securities and their weights in the portfolio, providing insights into asset composition and fund strategies. It is categorised as a Read tool in the Financial Modeling Prep MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Financial Modeling Prep MCP Server MCP server in PolicyLayer and add a rule for getFundHoldings: 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 Financial Modeling Prep MCP Server. Nothing to install.
getFundHoldings 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 getFundHoldings 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 getFundHoldings. 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.
getFundHoldings is provided by the Financial Modeling Prep MCP Server MCP server (vijitdaroch/financial-modeling-prep-mcp-server). 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 →