Use this when the user says
AI agents call richgo_guided_portfolio to retrieve information from Richgo Finance MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the incomplete description, the server's stated purpose is 'searching and analyzing Korean stocks' with no mention of transactional capabilities. The tool appears to guide users through portfolio analysis rather than commit financial transactions. It does not delete, modify accounts, or move money.
From the tool's definition Tool name is 'richgo_guided_portfolio' and description indicates it is used 'when the user says' — incomplete description, but the sibling tools on this server ('richgo_analyze_stock', 'richgo_get_ai_rankings', 'richgo_get_breakout',…
Attacks that exploit this kind of access
Use this when the user says. It is categorised as a Read tool in the Richgo Finance MCP MCP Server, which means it retrieves data without modifying state.
Register the Richgo Finance MCP server in PolicyLayer and add a rule for richgo_guided_portfolio: 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 Richgo Finance MCP. Nothing to install.
richgo_guided_portfolio 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 richgo_guided_portfolio 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 richgo_guided_portfolio. 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.
richgo_guided_portfolio is provided by the Richgo Finance MCP server (reallygood83/rfmcp). 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 →