Get performance metrics for all portfolios or a specific one
AI agents call portfolio_performance to retrieve information from Financial Data MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and returns performance metrics from existing portfolio data. It does not modify, execute trades, or create any records. The server description mentions 'portfolio management' broadly, but this specific tool is clearly a read/query operation with no financial transaction or data mutation implied.
From the tool's definition 'Get performance metrics for all portfolios or a specific one' — retrieves/queries performance data with no indication of side effects
Attacks that exploit this kind of access
Get performance metrics for all portfolios or a specific one. It is categorised as a Read tool in the Financial Data MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Financial Data MCP Server MCP server in PolicyLayer and add a rule for portfolio_performance: 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 Data MCP Server. Nothing to install.
portfolio_performance 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 portfolio_performance 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 portfolio_performance. 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.
portfolio_performance is provided by the Financial Data MCP Server MCP server (j1c4b/finance_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 →