生成投资组合报告
AI agents call generate_portfolio_report to retrieve information from Financial Report Generator MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and description indicate it generates a portfolio report, which is a read/aggregation operation producing a document. No evidence of writes, code execution, destructive actions, or financial transactions. Sibling tools suggest this server primarily reads financial data and generates reports.
From the tool's definition 生成投资组合报告 (Generate portfolio report) — report generation implies reading/aggregating data
Attacks that exploit this kind of access
生成投资组合报告. It is categorised as a Read tool in the Financial Report Generator MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Financial Report Generator MCP Server MCP server in PolicyLayer and add a rule for generate_portfolio_report: 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 Report Generator MCP Server. Nothing to install.
generate_portfolio_report 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 generate_portfolio_report 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 generate_portfolio_report. 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.
generate_portfolio_report is provided by the Financial Report Generator MCP Server MCP server (kennanyang/financial-report). 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 →